# liminalpepe/agent-guard-mcp

Source: https://glimind.com/server/glama%2Fliminalpepe%2Fagent-guard-mcp
Registry id: `glama/liminalpepe/agent-guard-mcp`
Status: unknown

## Tools (4)

- `check_package`: Check a single npm/PyPI package for typosquatting, slop, or other risks before adding it as a dependency.
- `check_workflow`: Check a GitHub Actions workflow for mutable action pins, compromised actions, curl|bash, pwn-requests, and secret exposure.
- `score_manifest`: Score a Cursor/Claude skill or MCP/Smithery plugin manifest for poison signatures, scope overreach, and drift.
- `verify_lockfile`: Scan every direct and transitive dependency in a lockfile for risks before running install.

Measured by Glimind (https://glimind.com): MCP handshake + tool list only, no tool is ever called. CC BY 4.0.
