# TrigGuard (npm · @trigguard/mcp)

Deterministic execution authorization for AI agents and automated systems.

- Trust score: 74/100 (medium)
- Change this week: +4
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-25

## Components

- npm · `@trigguard/mcp`: 74/100 (this document), [markdown](https://verifymcp.io/servers/trigguard-ai-trigguard/trigguard-mcp.md), [page](https://verifymcp.io/servers/trigguard-ai-trigguard/trigguard-mcp)

## Channel facts

- Registry: `npm`
- Package: `@trigguard/mcp`
- Version: `1.3.1`
- 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 2026-09-25.

- **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.
  - 31 of 99 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 19/100
  - Repository check failed: the declared repository URL returned HTTP 404.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (Apache-2.0).
  - Actively maintained (last published 35 days ago).
  - Security-disclosure policy not yet verified: we couldn't inspect the source repository.
- **Schema Quality & AI Usability**: 80/100
  - AI-judged instruction clarity (excellent).
  - Tool/resource definitions use about 659 tokens (~65/item across 10 items; 10 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 57/100
  - Stability observed for 17 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 10 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 10 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the TrigGuard MCP server?

TrigGuard runs locally as an npm package, launched with npx -y @trigguard/mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add trigguard-ai-trigguard -- npx -y @trigguard/mcp
```

### Cursor

```json
{
  "mcpServers": {
    "trigguard-ai-trigguard": {
      "command": "npx",
      "args": [
        "-y",
        "@trigguard/mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "trigguard-ai-trigguard": {
      "command": "npx",
      "args": [
        "-y",
        "@trigguard/mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add trigguard-ai-trigguard -- npx -y @trigguard/mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "trigguard-ai-trigguard": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@trigguard/mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add trigguard-ai-trigguard --command npx --arg -y --arg @trigguard/mcp
```

### Hermes

```yaml
mcp_servers:
  trigguard-ai-trigguard:
    command: "npx"
    args: ["-y", "@trigguard/mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "trigguard-ai-trigguard": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "@trigguard/mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add trigguard-ai-trigguard -t stdio -c npx -a -y @trigguard/mcp
```

### Other

```json
{
  "mcpServers": {
    "trigguard-ai-trigguard": {
      "command": "npx",
      "args": [
        "-y",
        "@trigguard/mcp"
      ]
    }
  }
}
```

## 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.

### 2026-09-25 (score 74, +1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-09-23 (score 73, +1)

No change was recorded against any check on this day. Stability & Change Management went from 47 to 50. That category is still filling its 30-day observation window: 14 days of observed history at the previous scan, 15 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-21 (score 72, +1)

No change was recorded against any check on this day. Stability & Change Management went from 40 to 43. That category is still filling its 30-day observation window: 12 days of observed history at the previous scan, 13 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-19 (score 71, +1)

No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-17 (score 70, +1)

No change was recorded against any check on this day. Stability & Change Management went from 27 to 30. That category is still filling its 30-day observation window: 8 days of observed history at the previous scan, 9 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-15 (score 69, +3)

- [functional improvement] Stability: unverified → 0.23

### 2026-09-09 (score 66, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-09-08 (score 51)

First indexed and scored.

## MCP tools (10)

### `authorize_action` (~130 tokens)

Request TrigGuard authority for an action. Returns PERMIT, DENY, SILENCE, or ESCALATE with execution receipt metadata and v1.1 explanation fields (reason_code, escalation_*, policy_version, evaluation_id). SILENCE is withhold/no-commitment; ESCALATE is an approval lifecycle. Neither is PERMIT. Requires TRIGGUARD_API_KEY (gateway API key).

Input parameters:

- `context` (object): Execution context (repository, environment, etc.)
- `subject` (string): Optional subject digest
- `surface` (string, required): Execution surface (e.g. deploy.release)

### `verify_receipt` (~85 tokens)

Verify a TrigGuard execution receipt by execution id. Optional include_receipt (default false) returns the receipt body. Requires gateway API key for authenticated lookup when the gateway enforces auth.

Input parameters:

- `execution_id` (string, required): Execution id (exec_…)
- `include_receipt` (boolean): When true, include the receipt document in the response (v1.1)

### `explain_decision` (~82 tokens)

Explain a TrigGuard authority decision using an execution_id and/or a prior authorize_result payload. Returns structured reason_code, missing requirements, and next actions. Read-only — does not authorize.

Input parameters:

- `authorize_result` (object): Optional prior authorize / gateway response object still in context
- `execution_id` (string): Execution id (exec_…) from authorize_action

### `get_surface` (~34 tokens)

Read execution surface registry metadata for one surface id (read-only, no policy evaluation).

Input parameters:

- `surface` (string, required): Surface id

### `list_surfaces` (~60 tokens)

List registered execution surfaces from the gateway well-known registry (or local registry override). Read-only discovery.

Input parameters:

- `limit` (number): Max surfaces to return (default 50, max 200)
- `prefix` (string): Optional surface id prefix filter

### `get_policy` (~55 tokens)

Read human-readable policy metadata for a surface from the bundled policy artifact. Does NOT evaluate live org policy — call authorize_action for PERMIT/DENY/SILENCE/ESCALATE.

Input parameters:

- `surface` (string, required): Surface id

### `list_org_policies` (~52 tokens)

List org policies from the TrigGuard control plane Policy Platform. Requires TRIGGUARD_SESSION_TOKEN + TRIGGUARD_ORG_ID (session JWT rail — not gateway API key alone). Read-only.

### `list_pending_policy_changes` (~37 tokens)

List pending policy change requests awaiting approval. Requires TRIGGUARD_SESSION_TOKEN + TRIGGUARD_ORG_ID. Read-only.

### `preview_policy_intent` (~67 tokens)

Compile-only preview of a policy intent against the Policy Platform. Requires TRIGGUARD_SESSION_TOKEN + TRIGGUARD_ORG_ID. Does not persist. Not a substitute for authorize_action.

Input parameters:

- `intent` (object, required): Policy intent JSON (same shape as tg policy --file)

### `health_check` (~57 tokens)

Check TrigGuard gateway reachability, policy engine status, registry hash, and whether API key / session JWT env vars are present (values are never returned).

Input parameters:

- `detailed` (boolean): When true, include raw /health body under details

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/trigguard-ai-trigguard/trigguard-mcp#diagnostics

## Score history

- 2026-09-25: 74
- 2026-09-24: 73
- 2026-09-23: 73
- 2026-09-22: 72
- 2026-09-21: 72
- 2026-09-20: 71
- 2026-09-19: 71
- 2026-09-18: 70
- 2026-09-17: 70
- 2026-09-16: 69
- 2026-09-15: 69
- 2026-09-14: 66
- 2026-09-13: 66
- 2026-09-12: 66
- 2026-09-11: 66
- 2026-09-10: 66
- 2026-09-09: 66
- 2026-09-08: 51

## Common questions

### What is the TrigGuard MCP server?

TrigGuard is an MCP server listed in the public MCP registry as io.github.TrigGuard-AI/trigguard. Deterministic execution authorization for AI agents and automated systems. This page covers its npm package (@trigguard/mcp).

### Is the TrigGuard MCP server safe to use?

TrigGuard scores 74 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 25 September 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 TrigGuard MCP server expose?

TrigGuard exposes 10 tools: authorize_action, verify_receipt, explain_decision, get_surface, list_surfaces, and 5 more. Their descriptions and schemas cost roughly 659 tokens of context every time the server is loaded.

### Is the TrigGuard MCP server still maintained?

TrigGuard is still listed as active in the MCP registry. We last reached this channel on 25 September 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 TrigGuard MCP server under?

TrigGuard 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

- npm package: https://www.npmjs.com/package/@trigguard/mcp
- Socket report: https://socket.dev/npm/package/@trigguard/mcp
- Website: https://trigguardai.com/
- Changelog RSS feed: https://verifymcp.io/servers/trigguard-ai-trigguard/trigguard-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/trigguard-ai-trigguard/trigguard-mcp.json
- HTML version of this page: https://verifymcp.io/servers/trigguard-ai-trigguard/trigguard-mcp