HumanMirror Outcome MCP
v1.0.0fr.humanmirror/outcome
Verified AI-agent outcomes: secret scanning, JSON cleanup, dedupe, anomaly and schema checks.
transport:streamable-http
Target client
run in your project directory
claude mcp add --transport http outcome https://humanmirror.fr/api/outcome/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.