Find agent tools (MCP servers, Claude Code skills, plugins, subagents, agent frameworks) in the Gatehouse registry. Filter by free-text query, category, kind, or vetting status. Returns a ranked list (vetted first) with each tool's status and health. Use get_tool for the full record or check_tool for a quick "is it safe" verdict.

The quick trust verdict for one agent tool: has Gatehouse hands-on vetted it, and what did it find? Call this at the moment of deciding whether to install/enable a tool. Returns the vetting status, the one-paragraph verdict, liveness, and the install line. For the full audit write-up use get_tool.

The complete Gatehouse record for one agent tool: metadata, compatibility, liveness/health, the vetting verdict, and — when it exists — the full first-hand audit write-up (how it was tested, what it injects, the caveats). Use check_tool instead if you only need the quick safe/not verdict.