Agent Guardrail MCP Server MCP
v0.1.2io.github.jarvisonm4/agent-guardrail
Action-level governance for AI agents -- control what they DO, not what they SAY
transport:stdio
runtime:pypi
Target client
run in your project directory
claude mcp add agent-guardrail -- uvx agent-guardrail
Adds it for this project only. Append --scope user to make it available everywhere. Claude Code docs
This listing does not declare its tools. Connect the server and your client will discover them on the handshake.