io.github.DSHCorrectover/agent-runtime-guard
NPM · AGENT-RUNTIME-GUARD
Agent 运行时全栈拦截: allow/deny tool calls, Ed25519 receipts, blocks RCE, theft, SSRF, injection. stdio.
Available components
Last scanned (19 hours ago)
Scores higher than 38% of npm servers
Category Security
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. How we score → Why this is hard to score →
Supply Chain Security100
- No malware found by supply-chain analysis.Pass
- No known CVEs affecting this package version or its production dependencies.Pass
- No install/post-install scripts declared.Pass
- No production dependencies, so there is no dependency health to assess. View diagnostics → Pass
Provenance & Transparency32
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- License check failed: the license (Elastic-2.0) isn't a recognized OSI-approved license. See how to fix → Fail
- Actively maintained (last published 12 days ago).Pass
- Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability77
- AI-judged instruction clarity (good).Pass
- Tool/resource definitions use about 562 tokens (~112/item across 5 items; 5 tools + 0 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management0
- Stability not yet verified: not enough scan history yet (needs a 30-day window).Unverified
Tool Coverage90
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 69% of tool parameters carry a description.Partial
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 5 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 5 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
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.
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 17 Oct 26 0
- Security disclosure: unverified → fail ▼ functional
- 16 Oct 26 0
- Security disclosure: fail → unverified ▼ functional
- 14 Oct 26 +31
- Injection markers: unverified → pass ▲ security
- First check of Judged manipulation: pass security
- Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window). security
- Tool coverage: unverified → 100 ▲ functional
- MCP protocol: unverified → pass ▲ functional
- First check of Schema quality: fail functional
- First check of Destructive annotations: pass functional
- First check of Schema quality: pass functional
- First check of Tool coverage: 69 functional
- First check of Schema quality: good functional
- 12 Oct 26 0
- Security disclosure: unverified → fail ▼ functional
- 11 Oct 26 0
- Security disclosure: fail → unverified ▼ functional
- 6 Oct 26 36
First indexed and scored.
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 18 Oct 2026 · Analysed npm/agent-runtime-guard@1.0.0
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | npm |
Background: How many MCP packages publish verified provenance →
Dependencies 0 packages
| Packages resolved | 0 |
|---|---|
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
audit_mcp_config Audit MCP configuration for security risks ~56
Audit an MCP client/server configuration JSON for security risks: plain HTTP, weak secrets, disabled TLS, missing commands. Returns structured issues with severity.
| Name | Type | Req | Description |
|---|---|---|---|
| config | object | yes | MCP configuration JSON (e.g. Claude Desktop config) |
No output schema declared.
No examples provided.
issue_evidence Issue signed CCS evidence receipt ~84
Issue a CCS evidence record for a tool call. Evidence is cryptographically bound (content_hash + evidence_hash), tamper-evident, independently verifiable. Issued for allowed AND denied calls.
| Name | Type | Req | Description |
|---|---|---|---|
| arguments | object | – | – |
| caller | object | yes | – |
| metadata | object | – | – |
| policy | object | – | – |
| tool | string | yes | – |
No output schema declared.
No examples provided.
verify_intent_binding Verify intent-to-arguments binding (L4) ~107
Verify that actual tool call arguments match a declared intent with zero tolerance. Catches cross-model parameter drift (planner says amount=100, executor writes amount=10000). No LLM needed — pure deterministic comparison. Supports exact match, numeric tolerance, and regex pattern binding modes.
| Name | Type | Req | Description |
|---|---|---|---|
| arguments | object | yes | Actual tool call arguments |
| intent | object | yes | Structured intent declaration from the agent framework |
| tool | string | yes | Tool being called, e.g. payments.send |
No output schema declared.
No examples provided.
verify_receipt Offline-verify a CCS signed receipt ~148
Offline-verify a CCS Ed25519-signed receipt. Auditors call this with a receipt JSON produced by issue_evidence or verify_intent_binding; it checks the signature against the embedded signer_public_key and reports whether the body was tampered with. Optionally pin an expected signer public key (PEM string or sha256: fingerprint) to reject receipts from untrusted signers.
| Name | Type | Req | Description |
|---|---|---|---|
| expected_signer | string | – | Optional. Either the expected PEM public key, or a sha256:<hex> fingerprint of the DER SPKI public key. |
| receipt | object | yes | The signed receipt object (must include signer_public_key, signature_alg, signature, and the signed body fields). |
No output schema declared.
No examples provided.
verify_tool_call Verify tool call (CCS 7-dimension) ~167
Verify an AI agent tool call against CCS 7 dimensions (Structure, Schema, Security, Identity, Integrity, Latency, Cost) plus semantic attack-chain analysis and math overflow detection. Returns verdict (allowed/denied) with detailed findings. DEFAULT MODE BLOCKS UNSAFE CALLS.
| Name | Type | Req | Description |
|---|---|---|---|
| arguments | object | – | Tool call arguments to verify |
| caller | object | – | Caller identity, e.g. {agent_id: 'agent-001'} |
| metadata | object | – | Optional metadata (execution_time_us, cost, request_id, etc.) |
| policy | object | – | Optional CCS policy override (allowed_tools, denied_tools, mode, budgets, etc.) |
| tool | string | yes | Tool name as namespace.action, e.g. 'shell.exec' or 'read.file' |
No output schema declared.
No examples provided.
How do I install the io.github.DSHCorrectover/agent-runtime-guard MCP server?
io.github.DSHCorrectover/agent-runtime-guard runs locally as an npm package, launched with npx -y agent-runtime-guard. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
npm · agent-runtime-guard
claude mcp add dshcorrectover-agent-runtime-guard -- npx -y agent-runtime-guard
What is the io.github.DSHCorrectover/agent-runtime-guard MCP server?
io.github.DSHCorrectover/agent-runtime-guard is an MCP server listed in the public MCP registry as io.github.DSHCorrectover/agent-runtime-guard. Agent 运行时全栈拦截: allow/deny tool calls, Ed25519 receipts, blocks RCE, theft, SSRF, injection. stdio. This page covers its npm package (agent-runtime-guard).
Is the io.github.DSHCorrectover/agent-runtime-guard MCP server safe to use?
io.github.DSHCorrectover/agent-runtime-guard scores 67 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 18 October 2026. It declares no install or post-install scripts. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the io.github.DSHCorrectover/agent-runtime-guard MCP server expose?
io.github.DSHCorrectover/agent-runtime-guard exposes 5 tools: verify_tool_call, issue_evidence, audit_mcp_config, verify_intent_binding, verify_receipt. Their descriptions and schemas cost roughly 562 tokens of context every time the server is loaded.
Is the io.github.DSHCorrectover/agent-runtime-guard MCP server still maintained?
io.github.DSHCorrectover/agent-runtime-guard is still listed as active in the MCP registry. We last reached this channel on 18 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What licence is the io.github.DSHCorrectover/agent-runtime-guard MCP server under?
io.github.DSHCorrectover/agent-runtime-guard declares the Elastic-2.0 licence, which is not on the OSI-approved list. Read the terms before using it at work, and note this covers the source only, not the cost of any service it calls.