# io.github.myshra777-ai/garuda (oci · ghcr.io/myshra777-ai/garuda-mcp)

Impact analysis, architecture rules and a tamper-evident ledger for AI coding agents.

- Trust score: 41/100 (low)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- oci · `ghcr.io/myshra777-ai/garuda-mcp`: 41/100 (this document), [markdown](https://verifymcp.io/servers/myshra777-ai-garuda/ghcr-io-myshra777-ai-garuda-mcp.md), [page](https://verifymcp.io/servers/myshra777-ai-garuda/ghcr-io-myshra777-ai-garuda-mcp)

## Channel facts

- Registry: `oci`
- Package: `ghcr.io/myshra777-ai/garuda-mcp`
- Version: `1.9.11`
- 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 2026-11-05.

- **Supply Chain Security**: 0/100
  - No malware scan is available for this kind of package: the supply-chain vendors we use do not cover it. This is a permanent gap in our coverage, not a finding about the package.
  - Known CVEs could not be checked: this artifact ships no SBOM or dependency manifest, so there is no dependency list to read.
  - Install-script risk not yet assessed.
  - Dependency health could not be checked: this artifact ships no SBOM or dependency manifest, so there is no dependency list to read.
- **Provenance & Transparency**: 48/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (Apache-2.0).
  - Actively maintained (last published 1 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 80/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 5236 tokens (~93/item across 56 items; 54 tools + 2 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 7/100
  - Stability observed for 2 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **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.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 54 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 56 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 60/100
  - Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 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

### How do I install the io.github.myshra777-ai/garuda MCP server?

io.github.myshra777-ai/garuda runs locally as a container image, launched with docker run --rm -i -e DATABASE_URL -e GARUDA_WORKSPACE ghcr.io/myshra777-ai/garuda-mcp:1.9.11. Ready-made configuration for Claude, Cursor, VS Code, Codex and 3 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add myshra777-ai-garuda -- docker run --rm -i -e DATABASE_URL -e GARUDA_WORKSPACE ghcr.io/myshra777-ai/garuda-mcp:1.9.11
```

This image reads DATABASE_URL and GARUDA_WORKSPACE. Set them in your client's env block for this server; docker run -e passes each one through to the container.

### Cursor

```json
{
  "mcpServers": {
    "myshra777-ai-garuda": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "-e",
        "DATABASE_URL",
        "-e",
        "GARUDA_WORKSPACE",
        "ghcr.io/myshra777-ai/garuda-mcp:1.9.11"
      ]
    }
  }
}
```

This image reads DATABASE_URL and GARUDA_WORKSPACE. Set them in your client's env block for this server; docker run -e passes each one through to the container.

### VS Code

```json
{
  "servers": {
    "myshra777-ai-garuda": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "-e",
        "DATABASE_URL",
        "-e",
        "GARUDA_WORKSPACE",
        "ghcr.io/myshra777-ai/garuda-mcp:1.9.11"
      ]
    }
  }
}
```

This image reads DATABASE_URL and GARUDA_WORKSPACE. Set them in your client's env block for this server; docker run -e passes each one through to the container.

### Codex

```bash
codex mcp add myshra777-ai-garuda -- docker run --rm -i -e DATABASE_URL -e GARUDA_WORKSPACE ghcr.io/myshra777-ai/garuda-mcp:1.9.11
```

This image reads DATABASE_URL and GARUDA_WORKSPACE. Set them in your client's env block for this server; docker run -e passes each one through to the container.

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "myshra777-ai-garuda": {
      "type": "local",
      "command": [
        "docker",
        "run",
        "--rm",
        "-i",
        "-e",
        "DATABASE_URL",
        "-e",
        "GARUDA_WORKSPACE",
        "ghcr.io/myshra777-ai/garuda-mcp:1.9.11"
      ],
      "enabled": true
    }
  }
}
```

This image reads DATABASE_URL and GARUDA_WORKSPACE. Set them in your client's env block for this server; docker run -e passes each one through to the container.

### Hermes

```yaml
mcp_servers:
  myshra777-ai-garuda:
    command: "docker"
    args: ["run", "--rm", "-i", "-e", "DATABASE_URL", "-e", "GARUDA_WORKSPACE", "ghcr.io/myshra777-ai/garuda-mcp:1.9.11"]
```

This image reads DATABASE_URL and GARUDA_WORKSPACE. Set them in your client's env block for this server; docker run -e passes each one through to the container.

### Netclaw

```json
{
  "McpServers": {
    "myshra777-ai-garuda": {
      "Transport": "stdio",
      "Command": "docker",
      "Arguments": [
        "run",
        "--rm",
        "-i",
        "-e",
        "DATABASE_URL",
        "-e",
        "GARUDA_WORKSPACE",
        "ghcr.io/myshra777-ai/garuda-mcp:1.9.11"
      ]
    }
  }
}
```

This image reads DATABASE_URL and GARUDA_WORKSPACE. Set them in your client's env block for this server; docker run -e passes each one through to the container.

### Other

```json
{
  "mcpServers": {
    "myshra777-ai-garuda": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "-e",
        "DATABASE_URL",
        "-e",
        "GARUDA_WORKSPACE",
        "ghcr.io/myshra777-ai/garuda-mcp:1.9.11"
      ]
    }
  }
}
```

This image reads DATABASE_URL and GARUDA_WORKSPACE. Set them in your client's env block for this server; docker run -e passes each one through to the container.

## 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.

### 2026-11-04 (score 41, +1)

No change was recorded against any check on this day. Stability & Change Management went from 0 to 3. That category is still filling its 30-day observation window: 0 days of observed history at the previous scan, 1 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-03 (score 40)

First indexed and scored.

## MCP tools (54)

### `garuda.briefing` (~97 tokens)

Session-start briefing: workspace state, policy verdict, epistemic counts, trust anchor, scale, top hubs, active policies, open contradictions, and what changed since this agent's last briefing. Read-only. Call this first.

Input parameters:

- `agent_id` (string): Caller-supplied agent identifier. Defaults to the MCP client name from the handshake.
- `workspace` (string): Workspace name. Defaults to the server's active workspace.

### `garuda.query` (~67 tokens)

Query the Garuda knowledge graph (entities, document claims, and decisions) with natural language keywords. Rejects raw SQL statements.

Input parameters:

- `query` (string, required): The natural language query
- `tenant_id` (string): Optional tenant ID
- `workspace` (string): Optional workspace name

### `garuda.get_lineage` (~123 tokens)

Get the full governance and AST lineage of a decision UUID, actor name (e.g. 'cli-operator'), or symbol name.

Input parameters:

- `actor` (string): Optional actor filter
- `decision_id` (string): Decision UUID, actor identifier, or symbol name
- `entity_id` (string): Optional entity UUID
- `name` (string): Optional entity/symbol name
- `symbol` (string): Optional symbol name (alias for decision_id)
- `tenant_id` (string): Tenant ID
- `workspace` (string): Optional workspace name

### `garuda.detect_contradictions` (~77 tokens)

Detect unresolved contradictions across decisions and ADR document claims in the tenant knowledge graph.

Input parameters:

- `scope` (string): Optional scope filter
- `status` (string): Optional status filter: open, resolved, or all (default open)
- `tenant_id` (string): Tenant ID
- `workspace` (string): Optional workspace name

### `garuda.get_impact` (~127 tokens)

Find what breaks if a decision UUID or code symbol (e.g. 'AppendLeafAndSealTx') is changed. Computes transitive blast radius and child decision impact.

Input parameters:

- `decision_id` (string): Decision UUID, entity UUID, or symbol name
- `entity_id` (string): Optional entity UUID or symbol name
- `name` (string): Alias for symbol name
- `symbol` (string): Target symbol name (e.g. 'AppendLeafAndSealTx')
- `tenant_id` (string): Tenant ID
- `workspace` (string): Optional workspace name

### `garuda.blast_radius` (~146 tokens)

Compute the blast radius of a symbol change: which entities consume the target entity, directly or transitively, up to a depth. Read-only. Returns a critical-first list and per-severity counts.

Input parameters:

- `depth` (integer): Max traversal depth. Default 3.
- `entity_id` (string): Target entity UUID or symbol name
- `min_confidence` (number): Minimum edge confidence. Default 0.50.
- `name` (string): Target symbol name (alternative to entity_id)
- `symbol` (string): Target symbol name (alternative to entity_id)
- `tenant_id` (string): Tenant UUID
- `workspace` (string): Workspace name

### `garuda.propose_decision` (~95 tokens)

Propose a new architectural decision (creates a draft).

Input parameters:

- `rationale` (string): Alias for statement
- `scope_domain` (string): Scope domain
- `scope_system` (string): Scope system
- `statement` (string): Normative decision statement or rationale
- `tenant_id` (string): Tenant ID
- `title` (string, required): Decision title
- `workspace` (string): Optional workspace name

### `garuda.policy.list` (~44 tokens)

List policies registered for a tenant. Read-only.

Input parameters:

- `tenant_id` (string): Tenant UUID; falls back to GARUDA_TENANT_ID env or default tenant

### `garuda.governance.status` (~71 tokens)

Aggregate governance state: top-level decision, active policies, documentation health, blocked_by list, and unified entity/claim counts. Read-only.

Input parameters:

- `tenant_id` (string): Tenant UUID
- `workspace` (string): Workspace name; falls back to GARUDA_WORKSPACE env or 'default'

### `garuda.check_drift` (~56 tokens)

Bidirectional documentation-to-code (doc_to_code) and code-to-documentation (code_to_doc) drift report. Read-only.

Input parameters:

- `tenant_id` (string): Tenant UUID
- `workspace` (string): Workspace name

### `garuda.query_claims` (~95 tokens)

Query document claims matching a subject and/or epistemic status (SUPPORTED, UNVERIFIED, CONTRADICTED). Read-only.

Input parameters:

- `status` (string): Optional status filter: SUPPORTED, UNVERIFIED, CONTRADICTED, or ALL
- `subject` (string): Filter by subject or object (substring)
- `tenant_id` (string): Tenant UUID
- `workspace` (string): Workspace name

### `garuda.policy.evaluate` (~123 tokens)

Dry-run the policy engine against a workspace and return deterministic policy decisions. Does NOT persist or Merkle-anchor. Use 'garuda policy evaluate' from the CLI to anchor a real governance decision.

Input parameters:

- `actor` (string): Optional actor identifier
- `policy_dir` (string): Directory containing policy YAML. Defaults to GARUDA_POLICY_DIR or ./policies
- `subject_id` (string): Optional subject ID
- `subject_kind` (string): Optional subject kind
- `tenant_id` (string): Tenant UUID
- `workspace` (string): Workspace name

### `garuda.verify_policy_evaluation` (~74 tokens)

Verify the Merkle inclusion proof for a persisted policy evaluation. Returns valid=true if the proof recomputes to the anchored root. Read-only; no side effects.

Input parameters:

- `evaluation_id` (string, required): Policy evaluation UUID returned by garuda policy evaluate --save
- `tenant_id` (string): Tenant UUID

### `garuda.verify_evidence` (~107 tokens)

Verify the RFC 6962 Merkle inclusion proof or SHA-256 evidence digest for a policy evaluation, evidence block, or decision UUID. Read-only; no side effects.

Input parameters:

- `decision_id` (string): Optional decision UUID
- `evaluation_id` (string): Alias for evidence_id (policy evaluation UUID)
- `evidence_id` (string): Evidence block or policy evaluation UUID
- `tenant_id` (string): Tenant UUID
- `workspace` (string): Optional workspace name

### `garuda.entities` (~92 tokens)

List semantic entities in a workspace. Filterable by package and kind. Read-only.

Input parameters:

- `kind` (string): Optional entity kind (struct, interface, function, method)
- `limit` (number): Max rows, default 100, cap 1000
- `package` (string): Optional package name substring
- `tenant_id` (string): Tenant UUID
- `workspace` (string): Workspace name

### `garuda.inspect` (~66 tokens)

Inspect one entity with its signature and incoming and outgoing relationships. Read-only.

Input parameters:

- `entity_id` (string, required): Entity UUID or symbol name
- `name` (string): Optional symbol name
- `tenant_id` (string): Tenant UUID
- `workspace` (string): Workspace name

### `garuda.subclasses` (~111 tokens)

List entities that inherit from or embed the subject. Uses INHERITS and EMBEDS claims. Read-only.

Input parameters:

- `entity_id` (string): Subject entity UUID
- `language` (string): Optional language filter (go, python, typescript)
- `limit` (number): Max rows, default 50, cap 500
- `name` (string): Subject entity name (alternative to entity_id)
- `tenant_id` (string): Tenant UUID
- `workspace` (string): Workspace name

### `garuda.implementers` (~89 tokens)

List entities that implement the subject interface. Uses IMPLEMENTS claims. Read-only.

Input parameters:

- `entity_id` (string): Subject interface UUID
- `limit` (number): Max rows, default 50, cap 500
- `name` (string): Subject interface name (alternative to entity_id)
- `tenant_id` (string): Tenant UUID
- `workspace` (string): Workspace name

### `garuda.neighbors` (~125 tokens)

List every entity connected to the subject in one hop, both incoming and outgoing directions. External stubs excluded by default. Read-only.

Input parameters:

- `edge_kinds` (array): Optional filter, e.g. ['CALLS','IMPORTS']
- `entity_id` (string, required): Subject entity UUID or symbol name
- `include_external` (boolean): Include external stubs (default false)
- `limit` (number): Max rows per direction, default 100, cap 500
- `tenant_id` (string): Tenant UUID
- `workspace` (string): Workspace name

### `garuda.create_task` (~145 tokens)

Create a new task and provision source/target agent UUIDs in the workspace so garuda.handoff and garuda.resume can operate on persisted UUIDs.

Input parameters:

- `description` (string): Optional task description
- `owner_agent_id` (string): Optional owner/source agent UUID or alias
- `priority` (number): Task priority (default 1)
- `scope_domain` (string): Optional scope domain
- `scope_system` (string): Optional scope system
- `target_agent_id` (string): Optional target agent UUID or alias
- `tenant_id` (string): Tenant UUID
- `title` (string, required): Task title
- `workspace` (string): Workspace name

### `garuda.handoff` (~143 tokens)

Initiate an atomic task handoff between two agents. Creates a checkpoint of the source agent's state, transfers task ownership, and transitions both agents' statuses. Call garuda.create_task first to provision UUIDs.

Input parameters:

- `checkpoint_data` (object): Optional serializable state to carry across the handoff
- `reason` (string): Optional human-readable reason
- `source_agent_id` (string, required): Source agent UUID or symbolic identifier
- `target_agent_id` (string, required): Target agent UUID or symbolic identifier
- `task_id` (string, required): Task UUID returned by garuda.create_task (or symbolic task identifier)
- `tenant_id` (string): Tenant UUID

### `garuda.resume` (~92 tokens)

Restore the state from an active checkpoint created by garuda.handoff, and mark the checkpoint as consumed. A second resume of the same checkpoint returns {status: 'not_found'}.

Input parameters:

- `agent_id` (string, required): Agent UUID or symbolic identifier performing the resume
- `checkpoint_id` (string, required): Checkpoint UUID or task identifier returned by garuda.handoff
- `tenant_id` (string): Tenant UUID

### `garuda.find_entity` (~169 tokens)

Find entities by exact name, regex name_pattern, kind, package, or file path. Returns status='not_found' with empty results when a filter matches 0 entities. Read-only.

Input parameters:

- `exported_only` (boolean): Only exported entities (default false)
- `file_path_contains` (string): File path substring
- `kind` (string): Entity kind (struct, interface, function, method, class, package)
- `limit` (number): Max rows, default 50, cap 500
- `name` (string): Exact or case-insensitive symbol name to match
- `name_pattern` (string): Regex against entity name
- `package` (string): Package name substring
- `tenant_id` (string): Tenant UUID
- `workspace` (string): Workspace name

### `garuda.talon_pre_edit` (~85 tokens)

MANDATORY pre-edit check: call before modifying any file or symbol. Returns transitive blast radius, callers, applicable ADR MUST/MUST_NOT claims, and active policy guardrails.

Input parameters:

- `target` (string): Target symbol name or file path about to be edited
- `tenant_id` (string): Tenant UUID
- `workspace` (string): Workspace name

### `garuda.talon_verify_edit` (~179 tokens)

MANDATORY post-edit verification gate: call immediately after modifying code. Runs in dry-run mode (side_effects=[]) by default; set save_to_ledger=true to append a Merkle ledger block (side_effects=['merkle_ledger_append']).

Input parameters:

- `diff` (string): Git revision range to check
- `files` (string): Comma-separated list of modified files
- `repo_dir` (string): Repository root directory (default .)
- `save_ledger` (boolean): Alias for save_to_ledger (default false)
- `save_to_ledger` (boolean): Explicitly anchor evaluation to RFC 6962 Merkle ledger (default false)
- `staged` (boolean): Check staged git index changes
- `tenant_id` (string): Tenant UUID
- `workspace` (string): Workspace name

### `garuda.disambiguate_logic` (~103 tokens)

Compare competing undocumented formulas across teams with 0.0-1.0 team weights summing to 1.00, surface criticality tiers (HIGH_SEVERE, MEDIUM, LOW), and explicit mode ('live_ast' vs 'fixture').

Input parameters:

- `concept` (string): Business concept or formula to disambiguate
- `team` (string): Active team context (ops, marketing, management)
- `workspace` (string): Workspace name

### `garuda.audit_data_discrepancy` (~143 tokens)

Audit cross-team business logic and metric number discrepancies in the Data & Logic Audit Ledger by tracing AST and SQL lineage before production deployment.

Input parameters:

- `metric` (string): Metric to reconcile
- `team_a_cr` (number): Team A reported metric value
- `team_a_crore` (number): Alias for team_a_cr
- `team_a_name` (string): Team A display name
- `team_b_cr` (number): Team B reported metric value
- `team_b_crore` (number): Alias for team_b_cr
- `team_b_name` (string): Team B display name
- `workspace` (string): Workspace name

### `garuda.reconcile_data_audit` (~92 tokens)

Record a reconciliation proposal for a flagged cross-team data discrepancy in the Data & Logic Audit Ledger. Requires GARUDA_MCP_APPROVER or CLI co-signing for human approval.

Input parameters:

- `approved_by` (string): Approving Lead Auditor or Architect (must match GARUDA_MCP_APPROVER)
- `audit_id` (string): Data audit item ID
- `workspace` (string): Workspace name

### `garuda.audit_financial_discrepancy` (~146 tokens)

Legacy alias for garuda.audit_data_discrepancy: audit cross-team business metric number discrepancies in the Data & Logic Audit Ledger.

Input parameters:

- `metric` (string): Business metric to reconcile
- `team_a_cr` (number): Team A reported metric value
- `team_a_crore` (number): Alias for team_a_cr
- `team_a_name` (string): Team A display name
- `team_b_cr` (number): Team B reported metric value
- `team_b_crore` (number): Alias for team_b_cr
- `team_b_name` (string): Team B display name
- `workspace` (string): Workspace name

### `garuda.synthesize_rulebook` (~100 tokens)

Synthesize unorganized repository architecture, surface criticality tiers, and multi-team formula weights into a structured draft Base Rulebook for human stakeholder review and approval.

Input parameters:

- `output` (string): Optional output file path (e.g. /tmp/smoke_rulebook.md)
- `output_path` (string): Alias for output file path
- `path` (string): Alias for output file path
- `workspace` (string): Workspace name

### `garuda.decide_logic_variant` (~175 tokens)

Propose or record a decision on a competing multi-team formula variant in PostgreSQL. Requires GARUDA_MCP_APPROVER or CLI co-signing for APPROVED_BY_HUMAN.

Input parameters:

- `approved_by` (string): Optional stakeholder identifier (must match GARUDA_MCP_APPROVER for direct approval)
- `custom_weight` (number): Optional custom weight (0.0 to 1.0)
- `decision_action` (string): APPROVED_BY_HUMAN, APPROVE_VARIANT, PROPOSE_VARIANT, FREEZE_SEVERE, SET_CUSTOM_WEIGHT, or RESET_TO_PENDING
- `team` (string): Active team role (ops, marketing, management)
- `variant_id` (string): Variant ID (e.g. loss_ratio_ops_v1)
- `workspace` (string): Workspace name

### `garuda.reconcile_financial_audit` (~75 tokens)

Legacy alias for garuda.reconcile_data_audit: record reconciliation for a flagged cross-team metric discrepancy in the Data & Logic Audit Ledger.

Input parameters:

- `approved_by` (string): Approving Auditor or Architect
- `audit_id` (string): Audit item ID
- `workspace` (string): Workspace name

### `garuda.approve_base_rulebook` (~107 tokens)

Propose or approve the synthesized Base Rulebook with an RFC 6962 SHA-256 digest. Requires GARUDA_MCP_APPROVER or CLI co-signing for human approval.

Input parameters:

- `approved_by` (string): Approver name or role
- `output` (string): Optional output file path
- `output_path` (string): Alias for output file path
- `path` (string): Alias for output file path
- `workspace` (string): Workspace name

### `garuda.criticality_tiers` (~126 tokens)

List or register 3-Tier Surface Criticality classifications (HIGH_SEVERE freeze, MEDIUM trade-off, LOW UI box alignment).

Input parameters:

- `criticality_tier` (string): Optional tier for custom surface (HIGH_SEVERE, MEDIUM, LOW)
- `package_pattern` (string): Optional package pattern for custom surface
- `surface_name` (string): Optional custom surface name to register
- `tier_filter` (string): Optional filter: HIGH_SEVERE, MEDIUM, LOW, or ALL
- `workspace` (string): Workspace name

### `garuda.docs_graph` (~66 tokens)

Retrieve the 4-Tier Document-to-Code & Guardrails Lineage Matrix (Documents -> Normative Rules -> Active Policies -> AST Symbols).

Input parameters:

- `doc_type` (string): Optional filter: ADR, SPEC, POLICY, or ALL
- `workspace` (string): Workspace name

### `garuda.docs_ingest` (~58 tokens)

Ingest Markdown ADRs or design specifications into document_claims and correlate them against workspace AST symbols.

Input parameters:

- `path` (string): File or directory path to ingest (default docs/adr)
- `workspace` (string): Workspace name

### `garuda.doctor_diagnose` (~45 tokens)

Run the Garuda System Doctor diagnostic suite across platform, PostgreSQL, Talon contract, and API gateway health.

Input parameters:

- `workspace` (string): Workspace name

### `garuda.build_matrix_check` (~76 tokens)

Verify the codebase across the 4-target Cross-Platform Build Matrix (linux/amd64, darwin/arm64, windows/amd64, cgo/purego) and return the deterministic BuildContext receipt.

Input parameters:

- `repo_dir` (string): Repository root path
- `workspace` (string): Workspace name

### `garuda.hygiene_report` (~69 tokens)

Run the static code hygiene analyzer on the workspace graph to report advisory unreferenced candidates, duplicate symbol names, and stdlib alternatives with structured file:line locations.

Input parameters:

- `limit` (number): Max findings per category (default 25)
- `workspace` (string): Workspace name

### `garuda.reset_audit_state` (~49 tokens)

Reset smoke-test or agent-proposed audit state in the workspace back to clean baseline.

Input parameters:

- `tenant_id` (string): Optional tenant UUID
- `workspace` (string): Workspace name

### `garuda.create_workspace` (~81 tokens)

Provision an isolated sandbox workspace (e.g. 'audit-sandbox') so mutating governance or audit checks can run safely without affecting the default workspace.

Input parameters:

- `name` (string): Alias for workspace name
- `tenant_id` (string): Optional tenant UUID
- `workspace` (string): New sandbox workspace name (e.g. 'audit-sandbox')

### `garuda.verify_receipt` (~79 tokens)

Recompute receipt_hash, graph_fingerprint, and policy_set_version from the current AST and git commit to cryptographically verify a pre-edit or guard receipt.

Input parameters:

- `receipt_hash` (string): Optional receipt_hash to verify against recomputed digest
- `tenant_id` (string): Optional tenant UUID
- `workspace` (string): Workspace name

### `garuda.diff_snapshots` (~57 tokens)

Compare the indexed graph snapshot receipt against current HEAD and list active vs superseded policies, commit sync state, and drift deltas.

Input parameters:

- `tenant_id` (string): Optional tenant UUID
- `workspace` (string): Workspace name

### `garuda.diff_impact` (~111 tokens)

Compute diff-level blast radius in one call: returns per-symbol impact with file, line_start, and source snippets for every symbol touched in the git diff.

Input parameters:

- `diff` (string): Git revision range (e.g. 'HEAD')
- `files` (string): Optional comma-separated file list
- `repo_dir` (string): Optional repository directory
- `staged` (boolean): Inspect staged changes
- `tenant_id` (string): Optional tenant UUID
- `workspace` (string): Workspace name

### `garuda.symbol_test_coverage` (~87 tokens)

Show which unit tests (*_test.go) and runtime traces exercise a symbol or package, explaining exported handler verification status.

Input parameters:

- `name` (string): Alias for symbol name
- `package` (string): Optional package filter
- `symbol` (string): Target symbol name
- `tenant_id` (string): Optional tenant UUID
- `workspace` (string): Workspace name

### `garuda.snapshot` (~55 tokens)

Return the current workspace snapshot ID, commit SHA, dirty-tree status, policy-set version, and freshness verdict (fresh, stale, dirty) in one lightweight call.

Input parameters:

- `workspace` (string): Workspace name (defaults to default)

### `garuda.explain_claim` (~55 tokens)

Return the compiler AST or policy derivation path and source snippet for a claim_id or symbol name.

Input parameters:

- `claim_id` (string): Claim UUID or symbol name to explain
- `workspace` (string): Workspace name

### `garuda.snippet` (~89 tokens)

Return hash-verified source lines around a symbol or file_path:line_start against the active snapshot.

Input parameters:

- `entity_id` (string): Entity UUID or symbol name
- `file_path` (string): Optional repository-relative file path
- `line_start` (number): Optional 1-indexed line number
- `name` (string): Symbol name
- `workspace` (string): Workspace name

### `garuda.summary` (~49 tokens)

Return a compact token-saving workspace summary (counts, active policies, and snapshot ID).

Input parameters:

- `scope` (string): Scope filter (default: production_only)
- `workspace` (string): Workspace name

### `garuda.owners` (~63 tokens)

Return the declared owner and team for an entity from the ownership mapping, or UNASSIGNED if undeclared.

Input parameters:

- `entity_id` (string): Entity UUID or symbol name
- `name` (string): Symbol name
- `workspace` (string): Workspace name

### `garuda.verify_claim` (~145 tokens)

Verify a structured edge (from_symbol, predicate, to_symbol) or prose claim against the indexed graph and return SUPPORTED, CONTRADICTED, or NOT_IN_GRAPH with a cryptographic receipt.

Input parameters:

- `claim` (string): Claim text (e.g. 'RefundHandler CALLS IdempotencyStore'), symbol, or claim_id
- `from_symbol` (string): Structured caller/source symbol name
- `predicate` (string): Edge predicate (CALLS, IMPORTS, IMPLEMENTS, INHERITS, REFERENCES, WRITES, READS)
- `to_symbol` (string): Structured callee/target symbol name
- `workspace` (string): Workspace name

### `garuda.test_coverage` (~58 tokens)

Alias for garuda.symbol_test_coverage: inspect which unit tests and runtime traces exercise a symbol.

Input parameters:

- `package` (string): Package filter
- `symbol` (string): Symbol name
- `workspace` (string): Workspace name

### `garuda.audit_export` (~72 tokens)

Export workspace decisions, policy evaluations, and Merkle block anchors as structured JSON or CSV for compliance filing.

Input parameters:

- `format` (string): Export format: 'json' or 'csv' (default 'json')
- `tenant_id` (string): Optional tenant UUID
- `workspace` (string): Workspace name

### `garuda.preflight_bundle` (~101 tokens)

Single-call token-saving pre-edit bundle combining snapshot freshness, talon_pre_edit briefing, test coverage, and declared ownership for a symbol or file.

Input parameters:

- `include_fixtures` (boolean): Include test/fixtures scope (default false)
- `symbol` (string): Alias for target symbol
- `target` (string): Target symbol or file path
- `tenant_id` (string): Optional tenant UUID
- `workspace` (string): Workspace name

## Diagnostics

Captured diagnostic sections: Provenance. The full working is on the page: https://verifymcp.io/servers/myshra777-ai-garuda/ghcr-io-myshra777-ai-garuda-mcp#diagnostics

## Score history

- 2026-11-05: 41
- 2026-11-04: 41
- 2026-11-03: 40

## Common questions

### What is the io.github.myshra777-ai/garuda MCP server?

io.github.myshra777-ai/garuda is an MCP server listed in the public MCP registry as io.github.myshra777-ai/garuda. Impact analysis, architecture rules and a tamper-evident ledger for AI coding agents. This page covers its container image (ghcr.io/myshra777-ai/garuda-mcp).

### Is the io.github.myshra777-ai/garuda MCP server safe to use?

io.github.myshra777-ai/garuda scores 41 out of 100 on VerifyMCP. 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.myshra777-ai/garuda MCP server expose?

io.github.myshra777-ai/garuda exposes 54 tools: garuda.briefing, garuda.query, garuda.get_lineage, garuda.detect_contradictions, garuda.get_impact, and 49 more. Their descriptions and schemas cost roughly 5,130 tokens of context every time the server is loaded.

### Is the io.github.myshra777-ai/garuda MCP server still maintained?

io.github.myshra777-ai/garuda is still listed as active in the MCP registry. We last reached this channel on 5 November 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.myshra777-ai/garuda MCP server under?

io.github.myshra777-ai/garuda declares the Apache-2.0 licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- GitHub Container Registry: https://ghcr.io/myshra777-ai/garuda-mcp
- Repository: https://github.com/myshra777-ai/garuda
- Changelog RSS feed: https://verifymcp.io/servers/myshra777-ai-garuda/ghcr-io-myshra777-ai-garuda-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/myshra777-ai-garuda/ghcr-io-myshra777-ai-garuda-mcp.json
- HTML version of this page: https://verifymcp.io/servers/myshra777-ai-garuda/ghcr-io-myshra777-ai-garuda-mcp