# REA (npm · rea-agents) Reverse engineer anything from your terminal or agent with one CLI and MCP server. - Trust score: 82/100 (high trust) - Registry status: active - Liveness: live - Owner verified: no - Last scored: 2026-08-12 ## Components - npm · `rea-agents`: 82/100 (this document), [markdown](https://verifymcp.io/servers/morluto-rea/rea-agents.md), [page](https://verifymcp.io/servers/morluto-rea/rea-agents) ## Channel facts - Registry: `npm` - Package: `rea-agents` - Version: `3.1.0` - Transport: `stdio` ## Trust breakdown How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog) Scored 2026-08-12. - **Supply Chain Security**: 98/100 - No malware found by supply-chain analysis. - No known CVEs affecting this package version or its production dependencies. - No install/post-install scripts declared. - 46 of 143 dependencies flagged as unhealthy. - **Provenance & Transparency**: 100/100 - Source repository is publicly reachable at the declared URL. - Cryptographically verified build provenance (signed, bound to morluto/rea). - Clear OSI-approved license (MIT). - Actively maintained (last published 2 days ago). - Publishes a security disclosure policy (SECURITY.md). - **Schema Quality & AI Usability**: 86/100 - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name). - AI-judged instruction clarity (good). - Context-footprint check failed: tool/resource definitions use about 13746 tokens (~116/item across 118 items; 116 tools + 2 resources), over budget; trim descriptions and params. - Tools include usage examples. - **Stability & Change Management**: 0/100 - Stability not yet verified: not enough scan history yet (needs a 30-day window). - **Tool Coverage**: 100/100 - 100% of tools have a non-trivial description (not blank, and not just the tool's name). - 100% of tool parameters carry a description. - Structured output schemas are declared (100% of tools); any adoption earns full credit. - **Capabilities**: 100/100 - Implements a current MCP spec version (2026-07-28). **Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm. ## Install ### Claude ```bash claude mcp add morluto-rea -- npx -y rea-agents ``` ### Codex ```bash codex mcp add morluto-rea -- npx -y rea-agents ``` ### opencode ```json { "$schema": "https://opencode.ai/config.json", "mcp": { "morluto-rea": { "type": "local", "command": [ "npx", "-y", "rea-agents" ], "enabled": true } } } ``` ### OpenClaw ```bash openclaw mcp add morluto-rea --command npx --arg -y --arg rea-agents ``` ### Hermes ```yaml mcp_servers: morluto-rea: command: "npx" args: ["-y", "rea-agents"] ``` ### Other ```json { "mcpServers": { "morluto-rea": { "command": "npx", "args": [ "-y", "rea-agents" ] } } } ``` ## Changelog Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims. ### 2026-08-11 (score 82, +4) - [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server ### 2026-08-10 (score 78, +15) - [security improvement] Malware scan: unverified → pass ### 2026-08-09 (score 63) First indexed and scored. ## MCP tools (116) ### `address_name` (~103 tokens) Address Name Resolve the primary analyzed name at a code or data address. Headless providers require an explicit address; GUI providers may default to their current cursor. Null means the provider has no primary name at that address. Input parameters: - `address` (string): A provider-normalized address; default memory uses 0x-prefixed hexadecimal - `document` (string): The document name - `unknown_registry_approved` (boolean): Explicit approval to record typed capability unavailability as a residual unknown Output parameters: - `evidence_id` (string) - `evidence_uri` (string) - `result` ### `comment` (~97 tokens) Comment Read the regular analysis comment at an address, defaulting to the current cursor. This is read-only and returns null when no comment exists; use set_comment to persist a finding. Input parameters: - `address` (string): A provider-normalized address; default memory uses 0x-prefixed hexadecimal - `document` (string): The document name - `unknown_registry_approved` (boolean): Explicit approval to record typed capability unavailability as a residual unknown Output parameters: - `evidence_id` (string) - `evidence_uri` (string) - `result` ### `current_address` (~66 tokens) Current Address Return Hopper's current cursor address for the selected document. Use only for interactive navigation state; prefer explicit addresses in reproducible investigations. Input parameters: - `document` (string): The document name - `unknown_registry_approved` (boolean): Explicit approval to record typed capability unavailability as a residual unknown Output parameters: - `evidence_id` (string) - `evidence_uri` (string) - `result` (string) ### `current_procedure` (~72 tokens) Current Procedure Return the analyzed procedure containing Hopper's current cursor. Use procedure_info or analyze_function next; this depends on GUI cursor state and is not an exhaustive lookup. Input parameters: - `document` (string): The document name - `unknown_registry_approved` (boolean): Explicit approval to record typed capability unavailability as a residual unknown Output parameters: - `evidence_id` (string) - `evidence_uri` (string) - `result` (string) ### `current_document` (~53 tokens) Current Document Return the document currently selected by REA's Hopper bridge. Use list_documents before switching when several documents are open. Input parameters: - `unknown_registry_approved` (boolean): Explicit approval to record typed capability unavailability as a residual unknown Output parameters: - `evidence_id` (string) - `evidence_uri` (string) - `result` (string) ### `goto_address` (~95 tokens) Goto Address Move Hopper's GUI cursor to a hexadecimal address and return the resolved address. This changes navigation state but not analysis data; use explicit-address tools for headless workflows. Input parameters: - `address` (string, required): A provider-normalized address; default memory uses 0x-prefixed hexadecimal - `document` (string): The document name - `unknown_registry_approved` (boolean): Explicit approval to record typed capability unavailability as a residual unknown Output parameters: - `evidence_id` (string) - `evidence_uri` (string) - `result` (string) ### `inline_comment` (~91 tokens) Inline Comment Read the inline instruction comment at an address, defaulting to the current cursor. Returns null when absent; use set_inline_comment to write one. Input parameters: - `address` (string): A provider-normalized address; default memory uses 0x-prefixed hexadecimal - `document` (string): The document name - `unknown_registry_approved` (boolean): Explicit approval to record typed capability unavailability as a residual unknown Output parameters: - `evidence_id` (string) - `evidence_uri` (string) - `result` ### `list_bookmarks` (~71 tokens) List Bookmarks List every bookmark in the selected Hopper document as address and name pairs. Use bookmarks as analyst-authored navigation aids; this does not discover code references. Input parameters: - `document` (string): The document name - `unknown_registry_approved` (boolean): Explicit approval to record typed capability unavailability as a residual unknown Output parameters: - `evidence_id` (string) - `evidence_uri` (string) - `result` (array) ### `list_documents` (~57 tokens) List Documents List provider program or document identities. Hopper may expose several documents; a Ghidra headless session contains exactly its one imported Program. Input parameters: - `unknown_registry_approved` (boolean): Explicit approval to record typed capability unavailability as a residual unknown Output parameters: - `evidence_id` (string) - `evidence_uri` (string) - `result` (array) ### `list_names` (~134 tokens) List Names Page through analyzed memory and external symbols as address/value pairs. Provider metadata distinguishes Ghidra primary, dynamic, external, type, and source facts when available; follow next_offset before claiming exhaustive coverage. Input parameters: - `address` (string): A provider-normalized address; default memory uses 0x-prefixed hexadecimal - `document` (string): The document name - `limit` (integer): Maximum number of results to return in this page. - `offset` (integer): Zero-based index of the first result to return. - `unknown_registry_approved` (boolean): Explicit approval to record typed capability unavailability as a residual unknown Output parameters: - `evidence_id` (string) - `evidence_uri` (string) - `result` (object) ### `list_procedures` (~112 tokens) List Procedures Page through analyzed procedures as address/value pairs after provider analysis. Ghidra metadata distinguishes thunks and external functions; follow next_offset for exhaustive coverage and use returned addresses in later function operations. Input parameters: - `document` (string): The document name - `limit` (integer): Maximum number of results to return in this page. - `offset` (integer): Zero-based index of the first result to return. - `unknown_registry_approved` (boolean): Explicit approval to record typed capability unavailability as a residual unknown Output parameters: - `evidence_id` (string) - `evidence_uri` (string) - `result` (object) ### `list_segments` (~75 tokens) List Segments List segments or memory blocks using exclusive end addresses. Ghidra reports block permissions, address space, image base, initialization, and overlay facts; Hopper marks unavailable permissions explicitly. Input parameters: - `document` (string): The document name - `unknown_registry_approved` (boolean): Explicit approval to record typed capability unavailability as a residual unknown Output parameters: - `evidence_id` (string) - `evidence_uri` (string) - `result` (array) ### `list_strings` (~139 tokens) List Strings Page through provider-defined strings, or filter to one address, as address/value pairs. Ghidra reports charset, missing-terminator status, byte length, and explicit value truncation; follow next_offset for exhaustive results. Input parameters: - `address` (string): A provider-normalized address; default memory uses 0x-prefixed hexadecimal - `document` (string): The document name - `limit` (integer): Maximum number of results to return in this page. - `offset` (integer): Zero-based index of the first result to return. - `unknown_registry_approved` (boolean): Explicit approval to record typed capability unavailability as a residual unknown Output parameters: - `evidence_id` (string) - `evidence_uri` (string) - `result` (object) ### `next_address` (~89 tokens) Next Address Return the next analyzed object address after an explicit address or current cursor. This is a navigation primitive, not instruction-flow or CFG analysis. Input parameters: - `address` (string): A provider-normalized address; default memory uses 0x-prefixed hexadecimal - `document` (string): The document name - `unknown_registry_approved` (boolean): Explicit approval to record typed capability unavailability as a residual unknown Output parameters: - `evidence_id` (string) - `evidence_uri` (string) - `result` (string) ### `prev_address` (~88 tokens) Prev Address Return the previous analyzed instruction start before an explicit address or current cursor. This is a navigation primitive and may fail at document boundaries. Input parameters: - `address` (string): A provider-normalized address; default memory uses 0x-prefixed hexadecimal - `document` (string): The document name - `unknown_registry_approved` (boolean): Explicit approval to record typed capability unavailability as a residual unknown Output parameters: - `evidence_id` (string) - `evidence_uri` (string) - `result` (string) ### `procedure_address` (~91 tokens) Procedure Address Resolve an unambiguous procedure symbol name or provider-normalized address to its canonical entry address. External address spaces remain explicit; use the result before xrefs, assembly, or decompilation. Input parameters: - `document` (string): The document name - `procedure` (string, required): The procedure name or address - `unknown_registry_approved` (boolean): Explicit approval to record typed capability unavailability as a residual unknown Output parameters: - `evidence_id` (string) - `evidence_uri` (string) - `result` (string) ### `procedure_assembly` (~90 tokens) Procedure Assembly Return assembly for one analyzed procedure identified by symbol or hexadecimal address. Use when pseudocode loses calling-convention or instruction-level detail; output is currently returned as one unpaginated string. Input parameters: - `document` (string): The document name - `procedure` (string, required): The procedure name or address - `unknown_registry_approved` (boolean): Explicit approval to record typed capability unavailability as a residual unknown Output parameters: - `evidence_id` (string) - `evidence_uri` (string) - `result` (string) ### `procedure_callees` (~91 tokens) Procedure Callees Return the provider's resolved direct callees for one procedure identified by symbol or address. Unresolved indirect calls may be absent; use analyze_function and typed references to preserve available edge uncertainty. Input parameters: - `document` (string): The document name - `procedure` (string, required): The procedure name or address - `unknown_registry_approved` (boolean): Explicit approval to record typed capability unavailability as a residual unknown Output parameters: - `evidence_id` (string) - `evidence_uri` (string) - `result` (array) ### `procedure_callers` (~81 tokens) Procedure Callers Return the provider's resolved direct callers for one procedure identified by symbol or address. Results reflect completed static analysis and may omit unresolved indirect references. Input parameters: - `document` (string): The document name - `procedure` (string, required): The procedure name or address - `unknown_registry_approved` (boolean): Explicit approval to record typed capability unavailability as a residual unknown Output parameters: - `evidence_id` (string) - `evidence_uri` (string) - `result` (array) ### `procedure_info` (~87 tokens) Procedure Info Return bounded metadata for one procedure identified by symbol or address: entrypoint, signature, locals, size, and block count. Follow with decompilation or assembly for behavior. Input parameters: - `document` (string): The document name - `procedure` (string, required): The procedure name or address - `unknown_registry_approved` (boolean): Explicit approval to record typed capability unavailability as a residual unknown Output parameters: - `evidence_id` (string) - `evidence_uri` (string) - `result` (object) ### `read_function_instructions` (~130 tokens) Read Function Instructions Read one offset-paginated window of raw instructions for an analyzed procedure without decompilation, caller discovery, or whole-program string/name scans. Use this fast path for instruction-level orientation; follow next_offset when truncated. Input parameters: - `document` (string): The document name - `limit` (integer): Maximum number of results to return in this page. - `offset` (integer): Zero-based index of the first result to return. - `procedure` (string, required): The procedure name or address - `unknown_registry_approved` (boolean): Explicit approval to record typed capability unavailability as a residual unknown Output parameters: - `evidence_id` (string) - `evidence_uri` (string) - `result` (object) ### `read_bytes` (~112 tokens) Read Bytes Read at most 4,096 analyzed bytes from one provider-normalized virtual address. The hexadecimal payload reports the exact returned length; incomplete reads remain explicit and unsupported provider APIs return typed capability unavailability. Input parameters: - `address` (string, required): A provider-normalized address; default memory uses 0x-prefixed hexadecimal - `document` (string): The document name - `length` (integer): Value for length. - `unknown_registry_approved` (boolean): Explicit approval to record typed capability unavailability as a residual unknown Output parameters: - `evidence_id` (string) - `evidence_uri` (string) - `result` (object) ### `address_to_file_offset` (~98 tokens) Address To File Offset Map one provider-normalized virtual address to its original nonnegative file offset. Unmapped addresses fail explicitly, and providers without an authoritative mapping API return typed capability unavailability. Input parameters: - `address` (string, required): A provider-normalized address; default memory uses 0x-prefixed hexadecimal - `document` (string): The document name - `unknown_registry_approved` (boolean): Explicit approval to record typed capability unavailability as a residual unknown Output parameters: - `evidence_id` (string) - `evidence_uri` (string) - `result` (object) ### `procedure_references` (~155 tokens) Procedure References Return a bounded set of raw incoming or outgoing reference edges for one procedure. Endpoint procedures are resolved only from provider containment; Ghidra preserves observed reference kinds while providers without kind authority mark them unavailable. Input parameters: - `direction` (string): Direction in which to traverse or compare relationships. - `document` (string): The document name - `limit` (integer): Maximum number of results to return in this page. - `max_instructions` (integer): Maximum permitted instructions for this operation. - `offset` (integer): Zero-based index of the first result to return. - `procedure` (string, required): The procedure name or address - `unknown_registry_approved` (boolean): Explicit approval to record typed capability unavailability as a residual unknown Output parameters: - `evidence_id` (string) - `evidence_uri` (string) - `result` (object) ### `procedure_pseudo_code` (~98 tokens) Procedure Pseudo Code Decompile one analyzed procedure by symbol name or provider-normalized address. Returns provider-specific pseudocode, never original source or cross-provider text equivalence, and may return null; request procedure_assembly when instruction precision matters. Input parameters: - `document` (string): The document name - `procedure` (string, required): The procedure name or address - `unknown_registry_approved` (boolean): Explicit approval to record typed capability unavailability as a residual unknown Output parameters: - `evidence_id` (string) - `evidence_uri` (string) - `result` ### `resolve_containing_procedure` (~106 tokens) Resolve Containing Procedure Resolve an arbitrary address, including an interior instruction or exact external entry, to its provider-analyzed containing procedure. A negative result distinguishes outside segments from not in a procedure and is never guessed from nearby symbols. Input parameters: - `address` (string, required): A provider-normalized address; default memory uses 0x-prefixed hexadecimal - `document` (string): The document name - `unknown_registry_approved` (boolean): Explicit approval to record typed capability unavailability as a residual unknown Output parameters: - `evidence_id` (string) - `evidence_uri` (string) - `result` ### `search_procedures` (~161 tokens) Search Procedures Search analyzed procedure names using literal matching by default or regex opt-in. Providers bound search work and reject regex constructs, paths, candidates, or cumulative work outside their finite budgets. Results are deterministic and offset-paginated. Input parameters: - `case_sensitive` (boolean): Whether to match case - `document` (string): The document name - `limit` (integer): Maximum number of results to return in this page. - `mode` (string): Operation mode that selects the requested behavior. - `offset` (integer): Zero-based index of the first result to return. - `pattern` (string, required): The literal text or bounded regex pattern to search for - `unknown_registry_approved` (boolean): Explicit approval to record typed capability unavailability as a residual unknown Output parameters: - `evidence_id` (string) - `evidence_uri` (string) - `result` (object) ### `search_strings` (~162 tokens) Search Strings Search analyzed strings using literal matching by default or regex opt-in. Providers bound search work and reject regex constructs, paths, candidates, or cumulative work outside their finite budgets. Results are deterministic, offset-paginated, and explicitly truncated. Input parameters: - `case_sensitive` (boolean): Whether to match case - `document` (string): The document name - `limit` (integer): Maximum number of results to return in this page. - `mode` (string): Operation mode that selects the requested behavior. - `offset` (integer): Zero-based index of the first result to return. - `pattern` (string, required): The literal text or bounded regex pattern to search for - `unknown_registry_approved` (boolean): Explicit approval to record typed capability unavailability as a residual unknown Output parameters: - `evidence_id` (string) - `evidence_uri` (string) - `result` (object) ### `set_address_name` (~108 tokens) Set Address Name Assign an analyst name to one hexadecimal address and report Hopper's boolean result. This mutates analysis metadata; read it back with address_name before relying on it. Input parameters: - `address` (string, required): A provider-normalized address; default memory uses 0x-prefixed hexadecimal - `document` (string): The document name - `name` (string, required): Exact name used by this operation. - `unknown_registry_approved` (boolean): Explicit approval to record typed capability unavailability as a residual unknown Output parameters: - `evidence_id` (string) - `evidence_uri` (string) - `result` (boolean) ### `set_addresses_names` (~83 tokens) Set Addresses Names Assign analyst names to an address/name map and return per-address success booleans. This mutates analysis metadata; use for bounded batches and verify failures individually. Input parameters: - `document` (string): The document name - `names` (object, required): Value for names. - `unknown_registry_approved` (boolean): Explicit approval to record typed capability unavailability as a residual unknown Output parameters: - `evidence_id` (string) - `evidence_uri` (string) - `result` (object) ### `set_bookmark` (~106 tokens) Set Bookmark Create or replace a bookmark at a hexadecimal address. This mutates navigation metadata; verify with list_bookmarks and do not treat bookmarks as binary evidence. Input parameters: - `address` (string, required): A provider-normalized address; default memory uses 0x-prefixed hexadecimal - `document` (string): The document name - `name` (string): Exact name used by this operation. - `unknown_registry_approved` (boolean): Explicit approval to record typed capability unavailability as a residual unknown Output parameters: - `evidence_id` (string) - `evidence_uri` (string) - `result` (boolean) ### `set_comment` (~107 tokens) Set Comment Write a regular analysis comment at a hexadecimal address and return whether readback matched. This mutates the Hopper document; use comments to record evidence IDs or reasoning. Input parameters: - `address` (string, required): A provider-normalized address; default memory uses 0x-prefixed hexadecimal - `comment` (string, required): Exact analyst comment text to write. - `document` (string): The document name - `unknown_registry_approved` (boolean): Explicit approval to record typed capability unavailability as a residual unknown Output parameters: - `evidence_id` (string) - `evidence_uri` (string) - `result` (boolean) ### `set_current_document` (~76 tokens) Set Current Document Select an already-open Hopper document by exact document name. This changes subsequent default-document routing; call list_documents first and prefer explicit document inputs where reproducibility matters. Input parameters: - `document` (string, required): Exact provider document or program identity. - `unknown_registry_approved` (boolean): Explicit approval to record typed capability unavailability as a residual unknown Output parameters: - `evidence_id` (string) - `evidence_uri` (string) - `result` (string) ### `set_inline_comment` (~103 tokens) Set Inline Comment Write an inline instruction comment at a hexadecimal address and return whether readback matched. This mutates analysis metadata; confirm with inline_comment. Input parameters: - `address` (string, required): A provider-normalized address; default memory uses 0x-prefixed hexadecimal - `comment` (string, required): Exact analyst comment text to write. - `document` (string): The document name - `unknown_registry_approved` (boolean): Explicit approval to record typed capability unavailability as a residual unknown Output parameters: - `evidence_id` (string) - `evidence_uri` (string) - `result` (boolean) ### `unset_bookmark` (~89 tokens) Unset Bookmark Remove the bookmark at a hexadecimal address and return whether it is absent. This mutates navigation metadata and does not alter binary bytes. Input parameters: - `address` (string, required): A provider-normalized address; default memory uses 0x-prefixed hexadecimal - `document` (string): The document name - `unknown_registry_approved` (boolean): Explicit approval to record typed capability unavailability as a residual unknown Output parameters: - `evidence_id` (string) - `evidence_uri` (string) - `result` (boolean) ### `xrefs` (~103 tokens) Xrefs Return analyzed references to a code or data address, defaulting to the current cursor. Use to connect strings, globals, selectors, and functions; bare addresses are untyped and indirect references may be incomplete. Input parameters: - `address` (string): A provider-normalized address; default memory uses 0x-prefixed hexadecimal - `document` (string): The document name - `unknown_registry_approved` (boolean): Explicit approval to record typed capability unavailability as a residual unknown Output parameters: - `evidence_id` (string) - `evidence_uri` (string) - `result` (array) ### `swift_classes` (~64 tokens) Swift Classes Discover legacy-mangled Swift class procedures after exhaustively paging analyzed procedures. Returns at most 100 entries and scans at most 5,000 symbols; use analyze_swift_types for other Swift kinds. Input parameters: - `pattern` (string): Text or bounded pattern used to filter matching results. Output parameters: - `evidence_id` (string) - `evidence_uri` (string) - `result` (object) ### `get_objc_classes` (~60 tokens) Get Objc Classes Discover and deduplicate Objective-C class labels after exhaustively paging names, optionally filtering by literal substring. Returns at most 100 classes; inspect matching metadata and references next. Input parameters: - `pattern` (string): Text or bounded pattern used to filter matching results. Output parameters: - `evidence_id` (string) - `evidence_uri` (string) - `result` (object) ### `get_objc_protocols` (~47 tokens) Get Objc Protocols Discover and deduplicate Objective-C and Swift protocol labels after exhaustively paging names. Returns at most 100 entries; use xrefs or analyze_function to connect a protocol to implementations. Output parameters: - `evidence_id` (string) - `evidence_uri` (string) - `result` (object) ### `batch_decompile` (~58 tokens) Batch Decompile Decompile up to 20 explicit procedure symbols or addresses concurrently. Returns ordered per-item ok/error variants and aggregate counts; use analyze_function for a richer single-function dossier. Input parameters: - `addresses` (array): Ordered provider-normalized procedure addresses to analyze. Output parameters: - `evidence_id` (string) - `evidence_uri` (string) - `result` (object) ### `get_call_graph` (~97 tokens) Get Call Graph Traverse the bound provider's caller or callee relationships from one symbol or address for at most five levels. Every node has an ok/error status and failures use safe typed projections; unresolved indirect calls may be missing and results are not a whole-program CFG. Input parameters: - `address` (string, required): A provider-normalized procedure address - `depth` (integer): Value for depth. - `direction` (string): Direction in which to traverse or compare relationships. Output parameters: - `evidence_id` (string) - `evidence_uri` (string) - `result` (object) ### `analyze_swift_types` (~53 tokens) Analyze Swift Types Categorize exhaustively paged procedure names into Swift classes, structs, enums, protocols, extensions, and other symbols. Scans at most 5,000 names and returns at most 50 entries per category. Output parameters: - `evidence_id` (string) - `evidence_uri` (string) - `result` (object) ### `find_xrefs_to_name` (~68 tokens) Find Xrefs To Name Resolve an exact name through the bound provider's exhaustively paged name inventory and return a resolved or unresolved result. Unresolved names use the stable name_not_found reason; this compact xref workflow returns address-only projections. Input parameters: - `name` (string, required): Exact name used by this operation. Output parameters: - `evidence_id` (string) - `evidence_uri` (string) - `result` ### `binary_overview` (~70 tokens) Binary Overview Use immediately after opening a target to summarize document, exhaustive procedure/string counts, and a bounded segment sample. detail controls segment fields and limit controls only the returned segment sample. Input parameters: - `detail` (string): Requested response detail level. - `limit` (integer): Maximum number of results to return in this page. Output parameters: - `evidence_id` (string) - `evidence_uri` (string) - `result` (object) ### `analyze_function` (~221 tokens) Analyze Function Preferred bounded analysis for one procedure symbol or address. Returns identity, provider-specific pseudocode, optional assembly, comments, calls, typed-or-explicitly-unavailable references, referenced strings/names, and local CFG blocks with exact truncation metadata. Providers with a structured decompiler model also expose native API boundary types, confidence, evidence, jump-table data/target addresses, and explicit decompiler-artifact labels. Input parameters: - `assembly_offset` (integer): Zero-based index of the first assembly to return. - `collection_offset` (object): Zero-based index of the first collection to return. - `include_assembly` (boolean): Whether to include assembly in the result. - `limit` (integer): Maximum number of results to return in this page. - `max_instructions` (integer): Maximum permitted instructions for this operation. - `max_pseudocode_chars` (integer): Maximum permitted pseudocode chars for this operation. - `procedure` (string, required): A procedure name or address - `pseudocode_offset` (integer): Zero-based index of the first pseudocode to return. Output parameters: - `evidence_id` (string) - `evidence_uri` (string) - `result` (object) ### `inspect_native_api` (~122 tokens) Inspect Native Api Reconstruct one native function boundary through inspectable substeps. Returns structured inferred return/parameter types with confidence and evidence, jump-table dispatch/data/target mappings, explicit decompiler-artifact labels, unsupported branches, and residual unknowns. Input parameters: - `max_instructions` (integer): Maximum permitted instructions for this operation. - `max_pseudocode_chars` (integer): Maximum permitted pseudocode chars for this operation. - `procedure` (string, required): A procedure name or address - `unknown_registry_approved` (boolean): Explicit approval to record unsupported native API branches durably Output parameters: - `evidence_id` (string) - `evidence_uri` (string) - `result` (object) ### `trace_feature` (~138 tokens) Trace Feature Trace a bounded literal feature query through matching strings and procedures, xrefs, and truthful containing-procedure resolution. Returns the operation budget, truncation, and residual unknowns; unknown_registry_approved: true records them durably without inferring reference kinds. Input parameters: - `case_sensitive` (boolean): Whether text matching distinguishes uppercase and lowercase. - `limit` (integer): Maximum number of results to return in this page. - `max_operations` (integer): Maximum permitted operations for this operation. - `query` (string, required): Non-empty feature or text query to investigate. - `unknown_registry_approved` (boolean): Explicit approval to record bounded residuals durably Output parameters: - `evidence_id` (string) - `evidence_uri` (string) - `result` (object) ### `find_code_for_string` (~138 tokens) Find Code For String Resolve one literal string query to bounded analyzed string entries, xrefs, and truthful containing-procedure candidates. Returns an Evidence ID, exact operation budget, truncation, and residual unknowns; it never infers reference kinds or runtime reachability. Input parameters: - `case_sensitive` (boolean): Whether text matching distinguishes uppercase and lowercase. - `limit` (integer): Maximum number of results to return in this page. - `max_operations` (integer): Maximum permitted operations for this operation. - `query` (string, required): Non-empty feature or text query to investigate. - `unknown_registry_approved` (boolean): Explicit approval to record bounded residuals durably Output parameters: - `evidence_id` (string) - `evidence_uri` (string) - `result` (object) ### `trace_call_path` (~170 tokens) Trace Call Path Trace a deterministic bounded caller or callee path from one exact procedure address, optionally stopping at a goal. Returns visited nodes, direct-call edges, one shortest traversal path, failures, frontier, consumed limits, an Evidence ID, and explicit residual unknowns without claiming unresolved indirect calls are absent. Input parameters: - `direction` (string): Direction in which to traverse or compare relationships. - `goal` (string): An optional provider-normalized destination address - `max_depth` (integer): Maximum permitted depth for this operation. - `max_nodes` (integer): Maximum permitted nodes for this operation. - `max_operations` (integer): Maximum permitted operations for this operation. - `start` (string, required): A provider-normalized procedure address - `unknown_registry_approved` (boolean): Explicit approval to record bounded residuals durably Output parameters: - `evidence_id` (string) - `evidence_uri` (string) - `result` (object) ### `inspect_macho` (~40 tokens) Inspect Macho Inspect Mach-O slices, load commands, imports, exports, dependencies, build metadata, segments, sections, permissions, and exact command provenance without launching Hopper. Output parameters: - `evidence_id` (string) - `evidence_uri` (string) - `result` (object) ### `inspect_signature` (~36 tokens) Inspect Signature Inspect the active artifact's code-signing identity, hashes, authorities, requirements, entitlements, hardened-runtime state, and bounded command provenance. Output parameters: - `evidence_id` (string) - `evidence_uri` (string) - `result` (object) ### `inspect_plist` (~54 tokens) Inspect Plist Parse a plist at a bounded relative path beneath the active artifact container. Symlink and traversal escapes are rejected; output is normalized JSON rather than plutil text. Input parameters: - `relative_path` (string): Local filesystem path for relative. Output parameters: - `evidence_id` (string) - `evidence_uri` (string) - `result` (object) ### `list_architectures` (~33 tokens) List Architectures List thin or universal Mach-O slices with offsets, sizes, alignment, explicit coverage, and bounded native-tool provenance. Output parameters: - `evidence_id` (string) - `evidence_uri` (string) - `result` (object) ### `demangle_swift` (~49 tokens) Demangle Swift Demangle an ordered bounded batch of Swift symbols without requiring Hopper. Each input returns demangled, unchanged, or invalid status. Input parameters: - `symbols` (array, required): Ordered bounded Swift symbols to demangle. Output parameters: - `evidence_id` (string) - `evidence_uri` (string) - `result` (object) ### `inventory_artifact` (~71 tokens) Inventory Artifact After open_binary binds a local archive, application package, or other artifact—or when one is already active—inventory it as a deterministic, content-addressed artifact graph. This tool accepts no path; in a target-free session open the target first. Returns bounded node and edge pages without extracting or mounting by default. Output parameters: - `evidence_id` (string) - `evidence_uri` (string) - `result` (object) ### `inspect_artifact` (~98 tokens) Inspect Artifact After open_binary binds a local archive, application package, or other artifact—or when one is already active—inspect it through one bounded, cancellable inventory substep. This tool accepts no path; in a target-free session open the target first. Returns the full substep Evidence and its ID, observations, derived relationships, hypotheses, contradictions, unexplored branches, limitations, and format-specific next probes. Any substep failure fails the whole call. Output parameters: - `evidence_id` (string) - `evidence_uri` (string) - `result` (object) ### `extract_artifact` (~206 tokens) Extract Artifact Extract selected graph artifacts beneath an explicit output root. Requires approval, rejects traversal and symlink escapes, never overwrites, enforces bomb limits, and verifies cleanup. Input parameters: - `approved` (boolean, required): Explicit operator approval to perform this operation. - `limit` (integer): Maximum number of results to return in this page. - `max_compression_ratio` (number): Maximum permitted compression ratio for this operation. - `max_depth` (integer): Maximum permitted depth for this operation. - `max_entries` (integer): Maximum permitted entries for this operation. - `max_entry_bytes` (integer): Maximum permitted entry bytes for this operation. - `max_path_bytes` (integer): Maximum permitted path bytes for this operation. - `max_total_bytes` (integer): Maximum permitted total bytes for this operation. - `occurrence_ids` (array, required): Value for occurrence ids. - `offset` (integer): Zero-based index of the first result to return. - `output_root` (string, required): Approved canonical filesystem output root. Output parameters: - `evidence_id` (string) - `evidence_uri` (string) - `result` (object) ### `inspect_managed_artifact` (~252 tokens) Inspect Managed Artifact Open and classify an explicit managed PE/CLI path, or inspect the active managed target, then inventory exact assembly/module identity, target framework evidence, references, resources, and custom attributes without loading or executing target code. Returns bounded pages and explicit partial or malformed coverage. Input parameters: - `attribute_limit` (integer): Maximum number of attribute entries to return. - `attribute_offset` (integer): Zero-based index of the first attribute to return. - `max_file_bytes` (integer): Maximum permitted file bytes for this operation. - `max_heap_item_bytes` (integer): Maximum permitted heap item bytes for this operation. - `max_metadata_bytes` (integer): Maximum permitted metadata bytes for this operation. - `max_table_rows` (integer): Maximum permitted table rows for this operation. - `path` (string): Managed PE/CLI path to open before inspection; omit only when a managed target is already active - `reference_limit` (integer): Maximum number of reference entries to return. - `reference_offset` (integer): Zero-based index of the first reference to return. - `resource_limit` (integer): Maximum number of resource entries to return. - `resource_offset` (integer): Zero-based index of the first resource to return. Output parameters: - `evidence_id` (string) - `evidence_uri` (string) - `result` (object) ### `inspect_managed_members` (~372 tokens) Inspect Managed Members Inspect bounded PE/CLI metadata members, signatures, raw CIL hashes, limited member-result-v1 decoded-instruction-tuple hashes, separately reported exception regions, call edges, and field-access anchors without loading or executing target code. Metadata tokens are reported as build-local coordinates bound to the artifact SHA-256 and MVID; the v1 tuple hash does not resolve them or fully commit control flow. Input parameters: - `edge_limit` (integer): Maximum number of edge entries to return. - `edge_offset` (integer): Zero-based index of the first edge to return. - `field_limit` (integer): Maximum number of field entries to return. - `field_offset` (integer): Zero-based index of the first field to return. - `instruction_anchor_limit` (integer): Maximum number of instruction anchor entries to return. - `max_file_bytes` (integer): Maximum permitted file bytes for this operation. - `max_heap_item_bytes` (integer): Maximum permitted heap item bytes for this operation. - `max_metadata_bytes` (integer): Maximum permitted metadata bytes for this operation. - `max_method_body_bytes` (integer): Maximum permitted method body bytes for this operation. - `max_method_instructions` (integer): Maximum permitted method instructions for this operation. - `max_table_rows` (integer): Maximum permitted table rows for this operation. - `member_ref_limit` (integer): Maximum number of member ref entries to return. - `member_ref_offset` (integer): Zero-based index of the first member ref to return. - `method_limit` (integer): Maximum number of method entries to return. - `method_offset` (integer): Zero-based index of the first method to return. - `type_limit` (integer): Maximum number of type entries to return. - `type_offset` (integer): Zero-based index of the first type to return. Output parameters: - `evidence_id` (string) - `evidence_uri` (string) - `result` (object) ### `inspect_managed_native_boundaries` (~228 tokens) Inspect Managed Native Boundaries Inspect PE/CLI ModuleRef, ImplMap/PInvoke declarations, CLI native-header indicators, and non-IL method implementation flags without loading or executing target code. Results are managed declarations and degraded native-boundary observations, not verified native exports or addresses. Input parameters: - `implementation_limit` (integer): Maximum number of implementation entries to return. - `implementation_offset` (integer): Zero-based index of the first implementation to return. - `import_limit` (integer): Maximum number of import entries to return. - `import_offset` (integer): Zero-based index of the first import to return. - `max_file_bytes` (integer): Maximum permitted file bytes for this operation. - `max_heap_item_bytes` (integer): Maximum permitted heap item bytes for this operation. - `max_metadata_bytes` (integer): Maximum permitted metadata bytes for this operation. - `max_table_rows` (integer): Maximum permitted table rows for this operation. - `module_ref_limit` (integer): Maximum number of module ref entries to return. - `module_ref_offset` (integer): Zero-based index of the first module ref to return. Output parameters: - `evidence_id` (string) - `evidence_uri` (string) - `result` (object) ### `compare_managed_members` (~156 tokens) Compare Managed Members Compare two authenticated inspect_managed_members Evidence records using unique-only decoded-CIL-v1/signature and structural method-shape tiers. Names are reported as observations but are not used as a matching basis; metadata tokens remain build-local coordinates bound to each artifact SHA-256 and MVID, and the v1 tuple digest does not itself remap them. Input parameters: - `left_evidence_id` (string, required): Session-owned inspect_managed_members Evidence ID - `limits` (object): Bounded resource-consumption and result-size limits for this operation. - `right_evidence_id` (string, required): Session-owned inspect_managed_members Evidence ID - `unknown_registry_approved` (boolean): Explicit approval to record bounded residual uncertainty in the session registry. Output parameters: - `evidence_id` (string) - `evidence_uri` (string) - `result` (object) ### `verify_managed_native_boundaries` (~139 tokens) Verify Managed Native Boundaries Verify managed P/Invoke/native-boundary declarations against authenticated native export or function Evidence without executing managed code or translating managed metadata tokens into native addresses. The workflow preserves declaration-only, verified, inferred, contradicted, and unresolved states. Input parameters: - `limits` (object): Bounded resource-consumption and result-size limits for this operation. - `managed_boundaries_evidence_id` (string, required): Session-owned inspect_managed_native_boundaries Evidence ID - `native_observation_evidence_ids` (array, required): Unique session-owned native observation Evidence IDs - `unknown_registry_approved` (boolean): Explicit approval to record bounded residual uncertainty in the session registry. Output parameters: - `evidence_id` (string) - `evidence_uri` (string) - `result` (object) ### `import_managed_reconstruction` (~154 tokens) Import Managed Reconstruction Import decompiler-produced managed reconstruction against authenticated inspect_managed_members Evidence. The workflow locks each method to artifact SHA-256, MVID, metadata token, signature hash, and the limited member-result-v1 decoded-IL tuple hash, records the decompiler identity and options, and marks C# or pseudocode as analyst inference rather than canonical byte observation. Input parameters: - `decompiler` (object, required): Value for decompiler. - `methods` (array, required): Value for methods. - `notes` (array): Value for notes. - `static_members_evidence_id` (string, required): Session-owned inspect_managed_members Evidence ID - `unknown_registry_approved` (boolean): Explicit approval to record bounded residual uncertainty in the session registry. Output parameters: - `evidence_id` (string) - `evidence_uri` (string) - `result` (object) ### `plan_managed_runtime_correlation` (~174 tokens) Plan Managed Runtime Correlation Prepare a separately authorized managed runtime-correlation admission plan from authenticated inspect_managed_members Evidence. The operation is default-disabled, requires the managed_runtime permission ceiling and grant, locks the exact artifact SHA-256, MVID, method signature, and limited member-result-v1 decoded-IL tuple hash, distinguishes attach/load/debugger/reflection/instrumentation effects, and records that no target code was executed. Input parameters: - `bounds` (object): Value for bounds. - `host` (object, required): Value for host. - `method` (object, required): Value for method. - `requested_effect` (string, required): Value for requested effect. - `static_members_evidence_id` (string, required): Session-owned inspect_managed_members Evidence ID - `unknown_registry_approved` (boolean): Explicit approval to record bounded residual uncertainty in the session registry. Output parameters: - `evidence_id` (string) - `evidence_uri` (string) - `result` (object) ### `project_managed_application_graph` (~61 tokens) Project Managed Application Graph Project authenticated managed artifact, member, and native-boundary Evidence into the provider-neutral application graph without executing managed code, loading assemblies, or translating managed metadata tokens to native addresses. The graph preserves managed static observations as managed-specific nodes linked to source Evidence. Output parameters: - `evidence_id` (string) - `evidence_uri` (string) - `result` (object) ### `list_browser_targets` (~126 tokens) List Browser Targets List bounded page targets from an approved user-owned loopback Chrome DevTools Protocol endpoint. Only targets whose current URL matches an approved exact origin are returned; URL credentials, query values, and fragments are redacted. Input parameters: - `allowed_origins` (array, required): Value for allowed origins. - `approved` (boolean, required): Explicit approval for browser observation - `cdp_endpoint` (string, required): Approved literal loopback Chrome DevTools Protocol endpoint. - `limit` (integer): Maximum number of results to return in this page. - `offset` (integer): Zero-based index of the first result to return. Output parameters: - `evidence_id` (string) - `evidence_uri` (string) - `result` (object) ### `inspect_web_page` (~66 tokens) Inspect Web Page Passively inspect one approved page target through CDP without evaluating JavaScript, navigating, clicking, closing, or mutating the page. Returns bounded DOM structure, accessibility, scripts, resources, attach-window network and console metadata, workers, and redacted storage inventory as Evidence v2. Output parameters: - `evidence_id` (string) - `evidence_uri` (string) - `result` (object) ### `analyze_web_bundle` (~62 tokens) Analyze Web Bundle Capture explicitly approved JavaScript source from one approved CDP page and statically derive a bounded chunk graph, route and endpoint candidates, vendor fingerprints, page-declared WebMCP metadata, and optional separately approved source-map evidence. JavaScript is parsed but never executed. Output parameters: - `evidence_id` (string) - `evidence_uri` (string) - `result` (object) ### `observe_web_session` (~142 tokens) Observe Web Session Arm a bounded CDP observation window while the user operates the page. Allows approved same-origin reload and SPA navigation, records ordered navigation, redirect, lifecycle, and failure metadata, and stops before retaining an out-of-policy destination. Input parameters: - `allowed_origins` (array, required): Value for allowed origins. - `approved` (boolean, required): Explicit operator approval to perform this operation. - `cdp_endpoint` (string, required): Approved literal loopback Chrome DevTools Protocol endpoint. - `max_timeline_events` (integer): Maximum permitted timeline events for this operation. - `observation_ms` (integer): Value for observation ms. - `target_id` (string, required): Exact authorized CDP target identifier. Output parameters: - `evidence_id` (string) - `evidence_uri` (string) - `result` (object) ### `discover_webmcp_tools` (~183 tokens) Discover Webmcp Tools Passively inventory page-registered WebMCP tools using the experimental CDP WebMCP domain. Metadata is bounded and page-declared-untrusted; REA never registers or invokes discovered tools. Input parameters: - `allowed_origins` (array, required): Value for allowed origins. - `approved` (boolean, required): Explicit operator approval to perform this operation. - `cdp_endpoint` (string, required): Approved literal loopback Chrome DevTools Protocol endpoint. - `max_schema_bytes` (integer): Maximum permitted schema bytes for this operation. - `max_schema_depth` (integer): Maximum permitted schema depth for this operation. - `max_schema_nodes` (integer): Maximum permitted schema nodes for this operation. - `max_tools` (integer): Maximum permitted tools for this operation. - `observation_ms` (integer): Value for observation ms. - `target_id` (string, required): Exact authorized CDP target identifier. Output parameters: - `evidence_id` (string) - `evidence_uri` (string) - `result` (object) ### `compare_web_captures` (~53 tokens) Compare Web Captures Compare either passive web captures or step-indexed browser scenarios. Scenario comparison aligns exact step IDs, records deterministic literal normalization, and exposes bounded artifact-level changes plus alignment failures. Missing or truncated evidence never proves equality. Output parameters: - `evidence_id` (string) - `evidence_uri` (string) - `result` ### `capture_web_screenshot` (~138 tokens) Capture Web Screenshot Capture the current visible viewport of one approved page as a bounded, content-addressed PNG artifact. Screenshot capture requires separate explicit approval and never scrolls, navigates, or evaluates page JavaScript. Input parameters: - `allowed_origins` (array, required): Value for allowed origins. - `approved` (boolean, required): Explicit operator approval to perform this operation. - `cdp_endpoint` (string, required): Approved literal loopback Chrome DevTools Protocol endpoint. - `maximum_image_bytes` (integer): Bounded byte count for maximum image. - `screenshot_approved` (boolean, required): Explicit operator approval for screenshot. - `target_id` (string, required): Exact authorized CDP target identifier. Output parameters: - `evidence_id` (string) - `evidence_uri` (string) - `result` (object) ### `compare_web_screenshots` (~95 tokens) Compare Web Screenshots Compare two self-verifying PNG screenshot artifacts with bounded local pixel metrics. Returns exact changed-pixel ratios and channel deltas without OCR or external services. Input parameters: - `after` (object, required): The later or right-hand observation to compare. - `before` (object, required): The earlier or left-hand observation to compare. - `channel_threshold` (integer): Value for channel threshold. - `maximum_pixels` (integer): Value for maximum pixels. Output parameters: - `evidence_id` (string) - `evidence_uri` (string) - `result` (object) ### `capture_browser_scenario` (~266 tokens) Capture Browser Scenario Run one approved, bounded browser scenario through Playwright. Launch mode owns and terminates a temporary browser profile; connect mode attaches to one exact loopback CDP target and disconnects without terminating the external browser. Only the fixed action vocabulary is accepted. Navigation, storage, requests, redirects, secrets, redaction, captures, and limits must be declared before execution. Returns step-indexed Evidence with screenshots, DOM, accessibility, URL/history/storage state, runtime events, explicit missing/truncated sections, and equality eligibility. Input parameters: - `actions` (array, required): Value for actions. - `allowed_origins` (array, required): Value for allowed origins. - `approved` (boolean, required): Explicit operator approval to perform this operation. - `browser` (required): Value for browser. - `capture` (object, required): Value for capture. - `environment` (object, required): Value for environment. - `limits` (object, required): Bounded resource-consumption and result-size limits for this operation. - `redaction` (object, required): Value for redaction. - `request_replay` (required): Value for request replay. - `schema_version` (number, required): Version of this structured result schema. - `secrets` (array): Value for secrets. - `start_url` (object, required): Value for start url. - `storage` (object, required): Value for storage. Output parameters: - `evidence_id` (string) - `evidence_uri` (string) - `result` (object) ### `list_electron_targets` (~128 tokens) List Electron Targets List Electron file:// page targets from an approved user-owned loopback CDP endpoint. Every path is canonicalized and must remain contained by an approved filesystem root, including after symlink resolution. Input parameters: - `allowed_file_roots` (array, required): Approved canonical filesystem allowed file roots. - `approved` (boolean, required): Explicit operator approval to perform this operation. - `cdp_endpoint` (string, required): Approved literal loopback Chrome DevTools Protocol endpoint. - `limit` (integer): Maximum number of results to return in this page. - `offset` (integer): Zero-based index of the first result to return. Output parameters: - `evidence_id` (string) - `evidence_uri` (string) - `result` (object) ### `inspect_electron_page` (~52 tokens) Inspect Electron Page Passively inspect one approved Electron file page through CDP. Returns root-confined frames, DOM structure, resource paths, and scripts without evaluating renderer JavaScript or invoking Electron APIs; script contents require separate approval. Output parameters: - `evidence_id` (string) - `evidence_uri` (string) - `result` (object) ### `analyze_javascript_application` (~192 tokens) Analyze Javascript Application Statically reconstruct one approved local ASAR or extracted JavaScript application without executing it. The default summary returns architecture/security counts, top evidence-backed findings, unknowns, and paged graph resource URIs; request detail=full only when the complete graph must be returned immediately. Identical inputs are deterministic, so do not repeat the call or reread full Evidence without a specific missing detail. Input parameters: - `approved` (boolean, required): Explicit operator approval to perform this operation. - `detail` (string): summary returns bounded findings and paged graph resource URIs; full returns the complete graph only when explicitly required - `format` (string): Declared input artifact format. - `input_path` (string, required): Local filesystem path for input. - `limits` (object): Bounded resource-consumption and result-size limits for this operation. - `source_map_read_approved` (boolean): Explicit operator approval for source map read. Output parameters: - `evidence_id` (string) - `evidence_uri` (string) - `result` ### `reconcile_javascript_runtime` (~145 tokens) Reconcile Javascript Runtime Reconcile verified static JavaScript application graphs with existing passive web/Electron CDP, passive V8 Inspector, or provider-owned active Electron Evidence. Active Electron captures contribute an explicitly partial target-only runtime record; they never invent renderer scripts, frames, workers, or execution claims. Exact captured-source digests take priority over caller-declared file/URL mappings; target, frame, script, and worker ambiguity remains explicit, and source-map authority stays separate. Input parameters: - `limits` (object): Bounded resource-consumption and result-size limits for this operation. - `runtime_observations` (array, required): Value for runtime observations. - `static_layers` (array, required): Value for static layers. Output parameters: - `evidence_id` (string) - `evidence_uri` (string) - `result` (object) ### `capture_electron_scenario` (~241 tokens) Capture Electron Scenario Use this for an explicitly approved, provider-owned Electron run when passive CDP or Inspector observation cannot exercise application behavior. REA owns startup and teardown, accepts bounded click/wait actions plus window-targeted renderer reload/crash and synthetic open-url/second-instance delivery, and returns correlated window/WebContents/process/preload/session/navigation/shell/IPC evidence without retaining payload values. Results identify observed and unavailable event families, coverage status, action targets, and truncation. External shell, navigation, permission, download, popup, updater, and OS-integration effects are blocked and recorded. Use passive Electron tools for observation-only work. Input parameters: - `actions` (array): Value for actions. - `application_path` (string, required): Local filesystem path for application. - `application_root` (string, required): Approved canonical filesystem application root. - `approved` (boolean, required): Explicit operator approval to perform this operation. - `args` (array): Value for args. - `executable_path` (string, required): Local filesystem path for executable. - `limits` (object): Bounded resource-consumption and result-size limits for this operation. - `schema_version` (number, required): Version of this structured result schema. Output parameters: - `evidence_id` (string) - `evidence_uri` (string) - `result` (object) ### `list_javascript_runtime_targets` (~139 tokens) List Javascript Runtime Targets List attachable Node/Electron V8 Inspector targets from one approved literal-loopback endpoint. Only targets inside exact canonical file roots or exact HTTP(S) origins are retained; excluded target locations never enter Evidence. Input parameters: - `allowed_file_roots` (array): Approved canonical filesystem allowed file roots. - `allowed_origins` (array): Value for allowed origins. - `approved` (boolean, required): Explicit operator approval to perform this operation. - `inspector_endpoint` (string, required): Value for inspector endpoint. - `limit` (integer): Maximum number of results to return in this page. - `offset` (integer): Zero-based index of the first result to return. Output parameters: - `evidence_id` (string) - `evidence_uri` (string) - `result` (object) ### `observe_javascript_runtime` (~207 tokens) Observe Javascript Runtime Attach passively to one exact approved Node/Electron V8 Inspector target and capture bounded Debugger.scriptParsed plus Runtime execution-context events. REA sends only Runtime.enable and Debugger.enable: it never evaluates, pauses, resumes, reads source, or instruments the target. require/import edges, EventEmitter activity, and Electron IPC remain explicit unknowns; reconcile the returned Evidence with static Application Graph Evidence using reconcile_javascript_runtime. Input parameters: - `allowed_file_roots` (array): Approved canonical filesystem allowed file roots. - `allowed_origins` (array): Value for allowed origins. - `approved` (boolean, required): Explicit operator approval to perform this operation. - `inspector_endpoint` (string, required): Value for inspector endpoint. - `limits` (object): Bounded resource-consumption and result-size limits for this operation. - `observation_ms` (integer): Value for observation ms. - `runtime_kind` (string, required): Value for runtime kind. - `target_id` (string, required): Exact authorized CDP target identifier. Output parameters: - `evidence_id` (string) - `evidence_uri` (string) - `result` (object) ### `trace_application_feature` (~78 tokens) Trace Application Feature Trace a typed literal seed through an authenticated JavaScript Application Graph supplied as full Evidence or an Evidence ID returned earlier in this session. Explicit direction, depth, node, edge, and path bounds apply. Original static, native, passive-runtime, inferred, and unknown authorities remain distinct; native addon handoffs never open a provider or execute the application. Output parameters: - `evidence_id` (string) - `evidence_uri` (string) - `result` (object) ### `trace_javascript_semantics` (~73 tokens) Trace Javascript Semantics Trace bounded static JavaScript data-flow, direct call/return, and closure relations from authenticated analyze_javascript_application v2 Evidence. Queries declare direction and exact node, relation, depth, function, module, and page limits. Dynamic or unsupported semantics remain explicit unknowns; static reachability never claims runtime execution. Output parameters: - `evidence_id` (string) - `evidence_uri` (string) - `result` (object) ### `compare_application_versions` (~80 tokens) Compare Application Versions Compare two authenticated JavaScript Application Graph versions supplied as full Evidence or Evidence IDs returned earlier in this session. Uses unique-only exact digest, module source digest, source-map identity, structural fingerprint, and non-module semantic-key tiers. Reports added, removed, changed, ambiguous, and unknown entities plus a bounded changed_from graph without fuzzy or module-ordinal pairing. Output parameters: - `evidence_id` (string) - `evidence_uri` (string) - `result` (object) ### `compare_source_to_bundle` (~87 tokens) Compare Source To Bundle Compare a cryptographically committed HistoricalSourceGraph/v1 with authenticated JavaScript Application Graph Evidence supplied directly or by session Evidence ID. Uses explicit exact-digest, source-map path, current-path, suffix, and basename signals with stable weights. Classifies unchanged, modified, removed, split, merged, duplicated, and unknown; incomplete coverage and ambiguous weak signals never become absence or forced matches. Output parameters: - `evidence_id` (string) - `evidence_uri` (string) - `result` (object) ### `compare_javascript_export_shapes` (~76 tokens) Compare Javascript Export Shapes Compare bounded static return shapes for one exact module/export selector on each authenticated JavaScript Application Graph, supplied as full Evidence or session Evidence IDs. Variants pair only by reciprocal unique literal discriminants; dynamic values, incomplete properties, and ambiguous variants remain unknown. Reports JSON Pointer changes and recommends controlled replay separately without executing JavaScript. Output parameters: - `evidence_id` (string) - `evidence_uri` (string) - `result` (object) ### `run_controlled_replay` (~73 tokens) Run Controlled Replay Plan or execute a content-bound extracted-module JavaScript replay inside the Linux Bubblewrap, seccomp, and cgroup boundary. Execution requires approved: true and the exact plan digest. Supports deterministic boundary cases and optional left/right differential comparison; observations have controlled-replay authority and do not claim real application runtime behavior. ### `prepare_node_characterization` (~119 tokens) Prepare Node Characterization Prepare a hash-bound Node/JavaScript characterization plan and deterministic reversible export transformation without executing target code. The exact source, selected byte range, runtime closure, sandbox profile, cases, and limits are committed for separate execution approval. Input parameters: - `expected_effect` (string, required): Expected effect used to reject stale or mismatched input. - `instrumentation` (object, required): Value for instrumentation. - `preparation_approved` (boolean, required): Explicit operator approval for preparation. - `replay` (object, required): Value for replay. - `selected_alias` (string, required): Value for selected alias. Output parameters: - `phase` (string) - `plan` (object) - `replay` (object) - `schema_version` (number) - `transformation` (object) - `transformation_evidence` ### `execute_node_characterization` (~92 tokens) Execute Node Characterization Recompute and execute one separately approved exact Node characterization plan in the owned controlled-replay boundary. Returns transformation, replay, cleanup, and provider-neutral characterization Evidence v2; stale plans fail before execution. Input parameters: - `approved_plan_sha256` (string, required): Exact SHA-256 digest of approved plan. - `execution_approved` (boolean, required): Explicit operator approval for execution. - `preparation` (object, required): Value for preparation. Output parameters: - `evidence` - `phase` (string) - `plan` (object) - `replay` (object) - `schema_version` (number) - `transformation` (object) - `transformation_evidence` ### `build_reconstruction_obligation_ledger` (~162 tokens) Build Reconstruction Obligation Ledger Generate one deterministic page of a ReconstructionObligationLedger/v1 from an authenticated Evidence v2 bundle, reviewed obligations, and an explicit reconstruction manifest. Static candidates remain candidates; duplicate ownership, missing original or reconstruction cases, missing parser/type, weak verifier authority, unenumerated claims, contradictions, dependencies, and residual unknowns fail closed. Every page carries the same full-ledger closure digest and typed per-obligation diagnostics. Input parameters: - `evidence_bundle` (object, required): Value for evidence bundle. - `limits` (object, required): Bounded resource-consumption and result-size limits for this operation. - `manifest` (object, required): Value for manifest. - `page` (object, required): Value for page. - `reviewed_obligations` (array, required): Value for reviewed obligations. Output parameters: - `evidence_id` (string) - `evidence_uri` (string) - `result` (object) ### `evaluate_reconstruction_readiness` (~271 tokens) Evaluate Reconstruction Readiness Evaluate the fixed nine-stage public reconstruction journey into a deterministic ReconstructionReadinessReport/v1. Exact capability limits, provider routing, CLI/MCP status parity, bounded authority, partial-order comparison, contradictions, obligation closure, cleanup, and replay digests fail closed. Aggregate pass is emitted only when every required stage and check passes with attributable Evidence. Input parameters: - `capabilities` (array, required): Value for capabilities. - `cleanup` (array, required): Value for cleanup. - `client` (object, required): Value for client. - `closure_history` (array, required): Value for closure history. - `comparisons` (array, required): Validated comparison Evidence records to aggregate. - `contradictions` (array, required): Value for contradictions. - `delegation_checks` (array, required): Value for delegation checks. - `evidence_bundle` (object, required): Value for evidence bundle. - `fixtures` (array, required): Value for fixtures. - `grants` (array, required): Value for grants. - `identity` (object, required): Value for identity. - `obligation_ledger` (object, required): Value for obligation ledger. - `operation_outcomes` (array, required): Value for operation outcomes. - `replay` (object, required): Value for replay. - `schema_version` (number, required): Version of this structured result schema. - `stages` (array, required): Value for stages. - `workflow_candidates` (array, required): Value for workflow candidates. Output parameters: - `evidence_id` (string) - `evidence_uri` (string) - `result` (object) ### `commit_reconstruction_coverage` (~104 tokens) Commit Reconstruction Coverage Atomically commit one canonical evidence-backed reconstruction coverage workspace revision under an approved root. CAS revisions reject lost updates; every Evidence and residual-unknown reference must resolve in the embedded canonical bundle. Input parameters: - `approved` (boolean, required): Explicit operator approval to perform this operation. - `expected_revision` (required): Expected revision used to reject stale or mismatched input. - `workspace` (object, required): Value for workspace. - `workspace_path` (string, required): Approved local path of the persistent investigation workspace. Output parameters: - `bytes` (integer) - `evidence_records` (integer) - `revision` (integer) - `revision_sha256` (string) - `workspace_id` (string) - `workspace_path` (string) ### `query_reconstruction_coverage` (~87 tokens) Query Reconstruction Coverage Evaluate one named reconstruction boundary from a canonical coverage workspace. Missing ownership or inventory is partial; stale, weak, truncated, skipped, or unresolved proof is unknown; contradictions, failed proof, missing owners, and authority routing fail closed. Input parameters: - `boundary_id` (string, required): Exact reconstruction boundary identifier to evaluate. - `workspace_path` (string, required): Approved local path of the persistent investigation workspace. Output parameters: - `boundary_id` (string) - `evidence_ids` (array) - `reasons` (array) - `recommended_probes` (array) - `status` (string) - `summary` (object) - `workspace_revision_sha256` (string) ### `open_binary` (~128 tokens) Open Binary Open a local executable, application bundle, archive, JavaScript, source map, plist, or analysis database after validation. provider_id selects one deep provider or deterministic auto selection; the binding remains stable until close or an explicit switch, with no failure fallback. An optional snapshot v2 is imported atomically and must match the binary identity, concrete provider, and canonical analysis profile exactly. Input parameters: - `path` (string, required): Local filesystem path used by this operation. - `provider_id`: Exact deep-analysis provider ID, or automatic selection when omitted. - `snapshot_path` (string): Local filesystem path for snapshot. Output parameters: - `result` (object) ### `close_binary` (~84 tokens) Close Binary Optionally write a provider-neutral analysis snapshot atomically, then close the active target and every provider resource started for it. Snapshot files require an operator-approved root and explicit overwrite; a failed save leaves the session open so cached analysis is not lost. Input parameters: - `overwrite` (boolean): Whether an existing destination may be replaced. - `snapshot_path` (string): Local filesystem path for snapshot. Output parameters: - `result` ### `binary_session` (~191 tokens) Binary Session Report compact target, provider, and alignment state without starting analysis. The default summary is the routing check agents should use; detail=capabilities returns one family-filtered availability page, while detail=full is reserved for complete provider diagnostics. Input parameters: - `capability_family` (string): Optional tool family for detail=capabilities - `cursor` (integer): Zero-based capability cursor for detail=capabilities - `detail` (string): summary returns routing state; capabilities returns one filtered tool-availability page; full returns complete diagnostics only when required - `expected_catalog_digest` (string): Expected catalog digest used to reject stale or mismatched input. - `expected_package_version` (string): Expected package version used to reject stale or mismatched input. - `expected_server_path` (string): Expected server path used to reject stale or mismatched input. - `limit` (integer): Maximum number of results to return in this page. Output parameters: - `result` ### `export_evidence_bundle` (~91 tokens) Export Evidence Bundle Atomically write the session's deterministic Evidence v2 bundle beneath an operator-approved root. Existing files require overwrite: true; records and manifests use canonical byte-stable ordering. For an in-session read, use snapshot_evidence_bundle and read its exact resource URI instead. Input parameters: - `overwrite` (boolean): Whether an existing destination may be replaced. - `path` (string, required): Local filesystem path used by this operation. Output parameters: - `result` (object) ### `import_evidence_bundle` (~62 tokens) Import Evidence Bundle Read a bounded local JSON bundle beneath an operator-approved root, validate every Evidence v2 ID and canonical manifest, then atomically merge it. Imported content is data only and is never executed. Input parameters: - `path` (string, required): Local filesystem path used by this operation. Output parameters: - `result` (object) ### `snapshot_evidence_bundle` (~68 tokens) Snapshot Evidence Bundle Retain the current canonical Evidence v2 bundle as an immutable session resource. Returns a compact digest summary and exact opaque URI; copy that URI unchanged and call MCP resources/read (Codex: read_mcp_resource) for the full bundle. Repeating an unchanged snapshot is idempotent. Output parameters: - `result` (object) ### `release_evidence_bundle` (~62 tokens) Release Evidence Bundle Release one immutable session-retained Evidence v2 bundle by exact digest. This is the recovery operation when bounded bundle retention is exhausted; releasing an unknown digest is idempotent and reports released: false. Input parameters: - `bundle_digest` (string, required): Value for bundle digest. Output parameters: - `result` (object) ### `capture_process_scenario` (~373 tokens) Capture Process Scenario Run one bounded process under a PTY using operator-approved executable and working roots. Produces Process Capture v4; legacy v3 captures cannot be upgraded and must be recaptured with this tool. Requires approved: true; unknown_registry_approved: true separately records capture residuals. Captures raw and xterm-rendered terminal frames, scripted interactions, lifecycle filesystem checkpoints, process ownership, declarative command shims, and loopback replay. Disabled unless operator policy enables it; not a security sandbox. Input parameters: - `approved` (boolean, required): Explicit per-call acknowledgement that this operation launches the target - `arguments` (array): Value for arguments. - `checkpoints` (array): Value for checkpoints. - `command_shims` (array): Value for command shims. - `environment` (object): Value for environment. - `events` (array): Value for events. - `executable` (string, required): Approved absolute path of the executable to run. - `filesystem_roots` (array): Approved canonical filesystem filesystem roots. - `idle_timeout_ms` (integer): Value for idle timeout ms. - `inherit_environment` (array): Value for inherit environment. - `limits` (object): Bounded resource-consumption and result-size limits for this operation. - `network_access` (string): Value for network access. - `normalization` (object): Value for normalization. - `reactive`: Value for reactive. - `replay` (object): Value for replay. - `secret_aliases` (array): Value for secret aliases. - `settle_ms` (integer): Value for settle ms. - `terminal` (object): Value for terminal. - `timeout_ms` (integer): Value for timeout ms. - `unknown_registry_approved` (boolean): Explicit approval to record capture residuals durably - `working_directory` (string, required): Value for working directory. Output parameters: - `evidence_id` (string) - `evidence_uri` (string) - `result` (object) ### `compare_process_captures` (~167 tokens) Compare Process Captures Compare two compatible Process Capture v4 observations across terminal, interaction, lifecycle, process, filesystem, command-shim, HTTP, and WebSocket evidence. Optional trace_spec validates exact events against an explicit partial order or finite trace language; concurrency is never inferred from timestamps or broad sorting. Missing, journal-free, or truncated observations are never treated as equivalent. Input parameters: - `left_evidence_id` (string, required): Exact Evidence v2 identifier for the left observation. - `max_capture_age_ms` (integer): Maximum permitted capture age ms for this operation. - `right_evidence_id` (string, required): Exact Evidence v2 identifier for the right observation. - `trace_spec` (object): Value for trace spec. - `unknown_registry_approved` (boolean): Explicit approval to record capture disagreement durably Output parameters: - `evidence_id` (string) - `evidence_uri` (string) - `result` (object) ### `compare_artifacts` (~147 tokens) Compare Artifacts Compare two bounded sets of inventory_artifact Evidence pages by logical occurrence path, content identity, metadata, and graph relations. Pages must share and satisfy their graph commitment; every delta cites both sets, and gaps yield truncated or unknown, never equivalence. Input parameters: - `left_evidence_ids` (array, required): Ordered Evidence v2 identifiers for the left observations. - `limit` (integer): Maximum number of results to return in this page. - `offset` (integer): Zero-based index of the first result to return. - `right_evidence_ids` (array, required): Ordered Evidence v2 identifiers for the right observations. - `unknown_registry_approved` (boolean): Explicit approval to record incomplete or differing evidence Output parameters: - `evidence_id` (string) - `evidence_uri` (string) - `result` (object) ### `compare_functions` (~147 tokens) Compare Functions Compare two explicit bounded sets of analyze_function Evidence pages across identity, exact provider text, calls, references, strings, and address-normalized CFG topology. Missing or provider-incompatible facets remain truncated or unknown; every conclusion cites both Evidence sets. Input parameters: - `left_evidence_ids` (array, required): Ordered Evidence v2 identifiers for the left observations. - `limit` (integer): Maximum number of results to return in this page. - `offset` (integer): Zero-based index of the first result to return. - `right_evidence_ids` (array, required): Ordered Evidence v2 identifiers for the right observations. - `unknown_registry_approved` (boolean): Explicit approval to record bounded residual uncertainty in the session registry. Output parameters: - `evidence_id` (string) - `evidence_uri` (string) - `result` (object) ### `compare_bundles` (~135 tokens) Compare Bundles Compare two canonical Evidence v2 bundles by exact record membership, explicit one-to-one observation pairs, and complete residual-unknown revision histories. Missing bundle members describe omission only, never behavioral equivalence; output is digest-anchored and deterministically paginated. Input parameters: - `left_bundle_path` (string, required): Local filesystem path for left bundle. - `limit` (integer): Maximum number of results to return in this page. - `offset` (integer): Zero-based index of the first result to return. - `record_pairs` (array): Value for record pairs. - `right_bundle_path` (string, required): Local filesystem path for right bundle. Output parameters: - `evidence_id` (string) - `evidence_uri` (string) - `result` (object) ### `find_changed_behavior` (~129 tokens) Find Changed Behavior Aggregate validated comparison Evidence, or automatically run and resume a persistent cross-version artifact investigation beneath an approved evidence root. Runtime observations remain distinct from static behavior candidates; missing or incomplete comparisons produce unresolved findings, never causal claims. Input parameters: - `comparisons` (array): Validated comparison Evidence records to aggregate. - `investigation_run`: Value for investigation run. - `limit` (integer): Maximum number of results to return in this page. - `offset` (integer): Zero-based index of the first result to return. - `unknown_registry_approved` (boolean): Explicit approval to record bounded residual uncertainty in the session registry. Output parameters: - `evidence_id` (string) - `evidence_uri` (string) - `result` (object) ### `build_call_path` (~165 tokens) Build Call Path Build bounded shortest-first direct-callee paths from explicit analyze_function Evidence groups using exact canonical addresses. Missing dossiers, incomplete callee pages, provider mixing, and depth frontiers remain unknown; every node and edge cites source Evidence. Input parameters: - `functions` (array, required): Value for functions. - `goal` (object, required): Value for goal. - `limit` (integer): Maximum number of results to return in this page. - `max_depth` (integer): Maximum permitted depth for this operation. - `max_paths` (integer): Maximum permitted paths for this operation. - `offset` (integer): Zero-based index of the first result to return. - `start` (object, required): Value for start. - `unknown_registry_approved` (boolean): Explicit approval to record bounded residual uncertainty in the session registry. Output parameters: - `evidence_id` (string) - `evidence_uri` (string) - `result` (object) ### `correlate_static_and_runtime` (~143 tokens) Correlate Static And Runtime Evaluate explicit caller-declared hypotheses between exact static comparison findings and runtime comparison dimensions. Similar names or paths are never auto-matched, consistent cochange never proves causality, and unknown or truncated inputs remain unresolved. Input parameters: - `limit` (integer): Maximum number of results to return in this page. - `mappings` (array, required): Value for mappings. - `offset` (integer): Zero-based index of the first result to return. - `runtime_comparisons` (array, required): Value for runtime comparisons. - `static_comparisons` (array, required): Value for static comparisons. - `unknown_registry_approved` (boolean): Explicit approval to record bounded residual uncertainty in the session registry. Output parameters: - `evidence_id` (string) - `evidence_uri` (string) - `result` (object) ### `verify_reconstruction` (~129 tokens) Verify Reconstruction Verify a finite typed behavioral and structural specification against a canonical Evidence bundle. Pass means every declared claim has complete comparable authority—not global source equivalence; changed claims fail and missing, limited, or unresolved evidence stays unknown. Input parameters: - `coverage` (object): Exact reconstruction-coverage commitment to verify. - `limit` (integer): Maximum number of results to return in this page. - `offset` (integer): Zero-based index of the first result to return. - `specification` (object, required): Value for specification. - `unknown_registry_approved` (boolean): Explicit approval to record bounded residual uncertainty in the session registry. Output parameters: - `evidence_id` (string) - `evidence_uri` (string) - `result` (object) ### `list_unknowns` (~136 tokens) List Unknowns List current residual-unknown heads in deterministic ID order, with optional exact status, severity, and domain filters. Pages default to 100 items; while has_more is true, pass next_offset as offset and continue until false. This is read-only; unresolved, contradicted, and non-truth dispositions remain distinct. Input parameters: - `domain` (string): Value for domain. - `limit` (integer): Maximum number of results to return in this page. - `offset` (integer): Zero-based index of the first result to return. - `severity` (string): Value for severity. - `status` (string): Current lifecycle or verification status. Output parameters: - `result` (object) ### `record_unknown` (~182 tokens) Record Unknown Create one deterministic residual unknown and immutable mutation evidence. Requires approved: true, validates all evidence and relationship references, and rejects duplicate stable identity. Input parameters: - `approved` (boolean, required): Explicit operator approval to perform this operation. - `contradicting_evidence_ids` (array): Ordered Evidence v2 identifiers for the contradicting observations. - `domain` (string, required): Value for domain. - `question` (string, required): Concrete unresolved question to retain for later investigation. - `recommended_probes` (array, required): Value for recommended probes. - `relationships` (array, required): Value for relationships. - `required_authority` (required): Value for required authority. - `required_confidence` (string, required): Value for required confidence. - `required_environment` (required): Value for required environment. - `severity` (string, required): Value for severity. - `supporting_evidence_ids` (array): Ordered Evidence v2 identifiers for the supporting observations. Output parameters: - `result` (object) ### `update_unknown` (~210 tokens) Update Unknown Append one immutable full-state revision and mutation evidence. Requires approved: true and exact expected_revision; stale concurrent writers fail instead of overwriting newer analysis. Input parameters: - `approved` (boolean, required): Explicit operator approval to perform this operation. - `contradicting_evidence_ids` (array, required): Ordered Evidence v2 identifiers for the contradicting observations. - `expected_revision` (integer, required): Expected revision used to reject stale or mismatched input. - `recommended_probes` (array, required): Value for recommended probes. - `relationships` (array, required): Value for relationships. - `required_authority` (required): Value for required authority. - `required_confidence` (string, required): Value for required confidence. - `required_environment` (required): Value for required environment. - `resolution` (required): Value for resolution. - `severity` (string, required): Value for severity. - `status` (string, required): Current lifecycle or verification status. - `supporting_evidence_ids` (array, required): Ordered Evidence v2 identifiers for the supporting observations. - `unknown_id` (string, required): Exact residual-unknown identifier. Output parameters: - `result` (object) ### `verify_unknown_resolution` (~59 tokens) Verify Unknown Resolution Revalidate the current residual-unknown head against live bundled evidence, exact authority/confidence/environment requirements, and revision integrity. Withdrawn and out-of-scope dispositions are not truth claims. Input parameters: - `unknown_id` (string, required): Exact residual-unknown identifier. Output parameters: - `result` (object) ### `run_replay_machine` (~86 tokens) Run Replay Machine Evaluate ordered HTTP and WebSocket events directly against one validated finite replay machine without opening sockets or launching a target. Returns every decision, a capture-value-free transition journal, one redacted action table entry per used transition, captured aliases, final state, and exact configured and consumed limits. Input parameters: - `events` (array, required): Value for events. - `machine` (object, required): Value for machine. Output parameters: - `result` (object) ### `get_navigation_context` (~73 tokens) Get Navigation Context Compose the selected document, current address, and containing/current procedure into one provider-neutral result. The result reflects sequential provider observations, not an atomic cursor snapshot; a cursor outside any procedure returns procedure: null. Scalar navigation getters remain available for evaluation and compatibility. Input parameters: - `document` (string): Exact provider document or program identity. Output parameters: - `result` (object) ### `inspect_address_context` (~78 tokens) Inspect Address Context Inspect one explicit reproducible address for its analyzed name, containing procedure, regular and inline comments, and matching bookmarks. Each unsupported facet returns a typed unavailable outcome; xrefs, assembly, and pseudocode remain separate bounded follow-ups. Input parameters: - `address` (string, required): Value for address. - `document` (string): Exact provider document or program identity. Output parameters: - `result` (object) ## Diagnostics Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/morluto-rea/rea-agents#diagnostics ## Score history - 2026-08-12: 82 - 2026-08-11: 82 - 2026-08-10: 78 - 2026-08-09: 63 ## Links - npm package: https://www.npmjs.com/package/rea-agents - Socket report: https://socket.dev/npm/package/rea-agents - Repository: https://github.com/morluto/rea - Changelog RSS feed: https://verifymcp.io/servers/morluto-rea/rea-agents.xml - Changelog JSON feed: https://verifymcp.io/servers/morluto-rea/rea-agents.json - HTML version of this page: https://verifymcp.io/servers/morluto-rea/rea-agents