# io.github.liminalpepe/agent-guard-mcp (npm · @liminallablibs/agent-guard-mcp)

Verify-before-act safety checks for AI agents: packages, lockfiles, manifests, CI workflows.

- Trust score: 66/100 (medium)
- Change this week: +23
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-04

## Components

- npm · `@liminallablibs/agent-guard-mcp`: 66/100 (this document), [markdown](https://verifymcp.io/servers/liminalpepe-agent-guard-mcp/liminallablibs-agent-guard-mcp.md), [page](https://verifymcp.io/servers/liminalpepe-agent-guard-mcp/liminallablibs-agent-guard-mcp)

## Channel facts

- Registry: `npm`
- Package: `@liminallablibs/agent-guard-mcp`
- Version: `0.2.1`
- 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 2026-08-04.

- **Supply Chain Security**: 83/100
  - No malware found by supply-chain analysis.
  - CVE check failed: a known medium-severity CVE affects hono 4.12.33, reached via @modelcontextprotocol/sdk > hono. A fixed version is available.
  - No install/post-install scripts declared.
  - Only part of the dependency tree could be resolved (94 of 98), so this covers what we could see, not the whole tree.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 33 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 70/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 668 tokens (~167/item across 4 items; 4 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 88/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 64% of tool parameters carry a description.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add liminalpepe-agent-guard-mcp -- npx -y @liminallablibs/agent-guard-mcp
```

### Codex

```bash
codex mcp add liminalpepe-agent-guard-mcp -- npx -y @liminallablibs/agent-guard-mcp
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add liminalpepe-agent-guard-mcp --command npx --arg -y --arg @liminallablibs/agent-guard-mcp
```

### Hermes

```yaml
mcp_servers:
  liminalpepe-agent-guard-mcp:
    command: "npx"
    args: ["-y", "@liminallablibs/agent-guard-mcp"]
```

### Other

```json
{
  "mcpServers": {
    "liminalpepe-agent-guard-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@liminallablibs/agent-guard-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.

### 2026-08-04 (score 66, +3)

- [security regression] CVE-2026-69207 affects this package: medium
- [security regression] Known CVEs: partial → fail
- [functional improvement] Stability: unverified → 0.27

### 2026-08-02 (score 63, +40)

- [security regression] Provenance: unverified → fail
- [security improvement] Install scripts: unverified → pass
- [security improvement] Known CVEs: unverified → partial
- [security improvement] Malware scan: unverified → pass
- [security] Stability: Stability not yet verified: we do not have a sandbox capture of the MCP schema this version of the package serves yet.
- [functional regression] Capabilities: pass → unverified
- [functional improvement] Schema quality: unverified → excellent
- [functional improvement] License: unverified → pass
- [functional improvement] Dependency health: unverified → partial
- [functional improvement] Maintenance: unverified → pass
- [functional] Licence: MIT

### 2026-08-01 (score 23, +5)

- [security] Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window).
- [functional improvement] MCP protocol: unverified → pass

### 2026-07-31 (score 18, −7)

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

### 2026-07-30 (score 25, −18)

- [security regression] Malware scan: pass → unverified

### 2026-07-27 (score 43)

First indexed and scored.

## MCP tools (4)

### `check_package` (~155 tokens)

Pre-install supply-chain gate for a single npm or PyPI package. Call BEFORE running npm install, pip install, or adding a dependency to package.json. Returns OK | SUSPICIOUS | DANGER (DANGER ~= NO-GO) with typosquat/slopsquat/hallucination flags. Read-only: queries public registries only; does not install anything. Do NOT use for full lockfile audits (use verify_lockfile) or CVE-only scans (use npm audit/OSV). If verdict is SUSPICIOUS or DANGER, stop and ask the user before installing.

Input parameters:

- `ecosystem` (string)
- `name` (string, required): Package name, e.g. "huggingface-cli".

### `verify_lockfile` (~156 tokens)

Scan an entire lockfile (direct + transitive deps) BEFORE npm/pip/yarn/pnpm install. Call when the user pastes or generates a lockfile, or before trusting an LLM-written package-lock.json / yarn.lock / pnpm-lock.yaml / poetry.lock / requirements.txt. Returns per-package OK | SUSPICIOUS | DANGER counts and flagged names. Read-only; pass raw file text, not a filesystem path. Do NOT use for a single new package (use check_package) or CI YAML (use check_workflow).

Input parameters:

- `ecosystem` (string): Optional; inferred from format.
- `format` (string, required)
- `lockfile_content` (string, required): Raw lockfile text (not a path).

### `score_manifest` (~206 tokens)

Score a third-party AI-agent extension manifest (skill/plugin manifest audit) BEFORE install. Call BEFORE installing a Cursor skill, Claude skill, MCP server package, or Smithery plugin. Detects poison/backdoor signatures, credential scope over-reach, and drift vs an approved baseline. Returns risk 0-100 and PROCEED | REVIEW | BLOCK. Supports manifest_type: cursor-skill | claude-skill | mcp-server | smithery-package. Read-only. Do NOT use for npm package names alone (use check_package). If BLOCK, refuse install until the user reviews findings. This skill/plugin coverage is unique to agent-guard.

Input parameters:

- `baseline_manifest` (string): Optional previously-approved manifest for drift scoring.
- `declared_purpose` (string): One-line stated purpose (for scope-overreach heuristics).
- `manifest_content` (string, required): Primary manifest text (SKILL.md, plugin.json, smithery.yaml, package.json).
- `manifest_type` (string, required)

### `check_workflow` (~151 tokens)

Validate CI workflow YAML (GitHub Actions / GitLab CI) BEFORE merging a PR that touches .github/workflows or GitLab CI. Call when reviewing or authoring CI pipelines. Flags mutable action pins (@v1), known-compromised actions, untrusted owners, curl|bash fetch-exec, pull_request_target pwn-request patterns, and secret exposure. Returns risk 0-100 and PROCEED | REVIEW | BLOCK. Read-only. Do NOT use for dependency lockfiles (use verify_lockfile). Default platform: github-actions. CI-workflow coverage is unique to agent-guard.

Input parameters:

- `platform` (string)
- `workflow_content` (string, required): Raw CI workflow YAML text.

## Diagnostics

Captured diagnostic sections: Provenance, Vulnerabilities, Dependencies. The full working is on the page: https://verifymcp.io/servers/liminalpepe-agent-guard-mcp/liminallablibs-agent-guard-mcp#diagnostics

## Score history

- 2026-08-04: 66
- 2026-08-03: 63
- 2026-08-02: 63
- 2026-08-01: 23
- 2026-07-31: 18
- 2026-07-30: 25
- 2026-07-28: 43
- 2026-07-27: 43

## Links

- npm package: https://www.npmjs.com/package/@liminallablibs/agent-guard-mcp
- Socket report: https://socket.dev/npm/package/@liminallablibs/agent-guard-mcp
- Repository: https://github.com/liminalpepe/agent-guard-mcp
- Changelog RSS feed: https://verifymcp.io/servers/liminalpepe-agent-guard-mcp/liminallablibs-agent-guard-mcp/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/liminalpepe-agent-guard-mcp/liminallablibs-agent-guard-mcp/changelog.json
- HTML version of this page: https://verifymcp.io/servers/liminalpepe-agent-guard-mcp/liminallablibs-agent-guard-mcp