rail score MCP
v1.1.1ai.responsibleailabs/rail-score
Responsible-AI guardrails for agents: scoring with policy, injection & PII detection, DPDP.
transport:streamable-http
Target client
run in your project directory
claude mcp add --transport http rail-score https://mcp.responsibleailabs.ai/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.