agent-guard-mcp

Verify-before-act safety tools for AI coding agents: check packages, lockfiles, skill/plugin manifests, and CI workflows before installing or merging.

CommunityOnlineNo sign-inGlobalFreeRead-only

What it can do

  • Check Package: 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; n
  • Verify Lockfile: Scan an entire lockfile (direct + transitive deps) for hallucinated / typosquatted / suspicious packages BEFORE running install. Call this instead of trusting an LLM-generated lockfil
  • Score Manifest: 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. Retu

What data it sees

Do you need an account

No: the server works without sign-in

Verify-before-act safety tools for AI coding agents: check packages, lockfiles, skill/plugin manifests, and CI workflows before installing or merging.

Server tool list (4)

Raw names from tools/list. Only developers need these.

check_packageCheck 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.
verify_lockfileScan an entire lockfile (direct + transitive deps) for hallucinated / typosquatted / suspicious packages BEFORE running install. Call this instead of trusting an LLM-generated lockfile.
score_manifestScore 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).
check_workflowValidate 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).