agent-guard-mcp
Provides tools to check the safety of npm packages and verify npm lockfiles before installation.
Provides tools to verify the safety of pnpm lockfiles before installation.
Provides tools to verify the safety of Poetry lockfiles before installation.
Provides tools to check the safety of PyPI packages and verify lockfiles before installation.
Provides tools to verify the safety of Yarn lockfiles before installation.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@agent-guard-mcp check if package 'lodash' is safe to add"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
agent-guard-mcp
One line: Verify-before-act safety for AI agents — check packages, lockfiles, skill manifests, and CI workflows before install or merge. Zero API keys. Zero config.
Scores Cursor/Claude skill manifests + GitHub Actions workflows — not just npm dependencies.
When you… | Call |
|
|
Review an LLM-generated lockfile |
|
Install a Cursor skill or MCP plugin |
|
Merge a PR touching |
|
Call these before installing a dependency, merging a CI change, or installing a third-party skill/plugin — so an agent refuses hallucinated packages, typosquats, poisoned manifests, and compromised CI actions.
Exposes four MCP tools (also available as a plain HTTP service):
Tool | Use before… | Returns |
| adding a single npm/PyPI dependency | OK / SUSPICIOUS / DANGER + typosquat/slop flags |
| running | scans every direct + transitive dep in a lockfile |
| installing a Cursor/Claude skill or MCP/Smithery plugin | poison-signature + scope-overreach + drift score 0–100 |
| merging a PR that touches CI | flags mutable action pins, compromised actions, curl|bash, pwn-requests, secret exposure |
Why
AI agents routinely hallucinate package names (slopsquatting), trust LLM-generated lockfiles, install unvetted skill packs, and pin CI actions to mutable tags. Each is a live supply-chain vector. This server gives an agent a cheap "is this safe?" call before it acts.
Related MCP server: repo-seatbelt
Install (MCP client)
{
"mcpServers": {
"agent-guard": { "command": "npx", "args": ["-y", "@liminallablibs/agent-guard-mcp@0.2.1"] }
}
}Agent rule (paste into Cursor Rules / CLAUDE.md)
Before installing any npm/PyPI package, running install from a lockfile, installing a third-party skill/MCP plugin, or merging CI workflow changes, call the agent-guard MCP tools (
check_package,verify_lockfile,score_manifest,check_workflow). If verdict is SUSPICIOUS, REVIEW, or BLOCK/DANGER, stop and show findings to the user — do not proceed.
Quick demo
npx -y @liminallablibs/agent-guard-mcp@0.2.1 # MCP clients spawn this via npx
# HTTP mirror:
npm run http && curl "http://localhost:8402/check?name=reactt&ecosystem=npm"
# → DANGER — typosquat of "react"Or run directly:
npm install
node src/mcp-server.mjs # stdio MCP server
npm run http # optional HTTP mirror on :8402HTTP endpoints (mirror of the MCP tools)
GET /check?name=<pkg>&ecosystem=<npm|pypi>POST /check-lockfile {lockfile_content, format}— format ∈ package-lock.json | yarn.lock | pnpm-lock.yaml | poetry.lock | requirements.txtPOST /score-manifest {manifest_type, manifest_content}POST /check-workflow {workflow_content}
License
MIT.
Available Tools
4 toolscheck_packageA
Check whether a single package exists and assess slopsquat/typosquat risk BEFORE installing it. Returns OK/SUSPICIOUS/DANGER + risk + flags. Nonexistent names are likely hallucinated; names 1-2 chars from a popular package are likely typosquats.
Inputs: name (required), ecosystem.
check_workflowA
Validate a CI workflow (GitHub Actions / GitLab CI YAML) BEFORE merging a PR that touches it. Flags mutable action pins, known-compromised actions, untrusted owners, curl|bash fetch-exec, pull_request_target pwn-requests, and secret exposure. Returns risk 0-100 + merge recommendation (PROCEED/REVIEW/BLOCK).
Inputs: workflow_content (required), platform.
score_manifestA
Score a Cursor/Claude skill or MCP/Smithery plugin manifest for poison/backdoor signatures, credential scope over-reach, and drift BEFORE installing a third-party agent extension. Returns risk 0-100 + install recommendation (PROCEED/REVIEW/BLOCK).
Inputs: manifest_type (required), manifest_content (required), declared_purpose, baseline_manifest.
verify_lockfileB
Scan an entire lockfile (direct + transitive deps) for hallucinated / typosquatted / suspicious packages BEFORE running install. Call this instead of trusting an LLM-generated lockfile.
Inputs: format (required), lockfile_content (required), ecosystem.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 4 tools
Each tool targets a distinct security artifact (package, workflow, manifest, lockfile) with no overlap in purpose. An agent can clearly distinguish which tool to call for each verification task.
Tool names follow a verb_noun pattern: 'check_package', 'check_workflow', 'score_manifest', 'verify_lockfile'. While 'check' is used twice, 'score' and 'verify' are different but still descriptive, maintaining a clear and predictable structure.
With 4 tools, the set is concise and focused on common pre-installation and pre-merge security checks. Each tool addresses a specific need without unnecessary bloat, making the surface easy to navigate.
The tool set covers major security vetting areas: package typosquatting, CI workflow integrity, manifest backdoor analysis, and lockfile scanning. Minor gaps like environment or dependency drift checks exist, but the core use cases are well-addressed.
Related MCP Connectors
Free MCP security tools for AI coding agents. Check npm/PyPI package versions, identify known OSV vulnerabilities, compare with the latest releases, and review up to 3 dependencies before deployment.
Check an npm/PyPI package before an AI agent installs it: 5 focused supply-chain tools.
Package verdicts for AI coding agents: check npm, PyPI, Go and NuGet installs before they run.
Check packages for CVEs, slopsquatting, and CISA KEV before your AI agent installs them.
Related MCP Servers
- AlicenseAqualityBmaintenanceMCP security server for AI coding agents. 12 tools: pre-install guardian, vulnerability audit, supply-chain attack detection via static code analysis, and CycloneDX 1.6 SBOM generation. Zero runtime dependencies.15109 npm15Apache 2.0
- AlicenseNot gradedqualityDmaintenanceRuntime safety guardrails for AI coding agents. Checks file access, validates shell commands, and scores your repo's AI safety — all via MCP.15 npm8MIT
- AlicenseAqualityAmaintenanceAgent trust & data safety MCP: PII/secret redaction, email validation, sanctions screening, and OSV vulnerability checks for AI agents.2130MIT
- AlicenseNot gradedqualityCmaintenanceEnables AI coding agents to scan projects or changed files for risky leftovers like hallucinated packages, exposed secrets, truncated code, and unfinished stubs, and to verify that packages exist before installing them.17 npmMIT