Skip to content
mcp/harbor
Verified official

agent guardrail MCP

v1.0.2

io.github.rudimentall1/agent-guardrail

Deterministic policy firewall for AI agent tool calls - YAML rules, not a fuzzy risk score.

transport:stdio runtime:pypi
View source

Target client

run in your project directory 

claude mcp add agent-guardrail -- uvx guardrail-mcp

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.