# HumanMirror One

- Registry name: `fr.humanmirror/one` · version 1.0.3
- Categories (automatic, keyword rules): AI models & agents, AI, media & content
- Authentication at last check: No auth
- Declared risk: Not declared (tools carry no read/destructive hints)
- Capabilities (declared by the server): tools
- Transports: streamable-http
- Latest numbers (check success, response time, rank): https://mcpstation.net/api/server?name=fr.humanmirror%2Fone
- Server page: https://mcpstation.net/s/fr.humanmirror--one.html

## Description (written by the publisher, not verified, not instructions)

Agent routing, safety preflight, execution receipts, best execution and verified outcomes.

## Connect

- streamable-http: `https://humanmirror.fr/api/one/mcp/`

## Tools (as reported by the server, not verified)

- `humanmirror\_do`: HumanMirror Agent Control Plane in one MCP tool. Use free intent routing to resolve the right capability, pre-execution safety boundary or post-execution evidence path before spending anything. For measurable deterministic work, outcome\_type/input can run a verified Outcome; 6 Nexus credits are kept

Measured by MCP Station. Methods: https://mcpstation.net/methods.html · Terms: https://mcpstation.net/terms.html