# remirror \(返照） — psyche audits for AI agents

- Registry name: `io.github.OntoDistro/remirror` · version 1.0.0
- 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): experimental, prompts, resources, tools
- Transports: streamable-http
- Latest numbers (check success, response time, rank): https://mcpstation.net/api/server?name=io.github.OntoDistro%2Fremirror
- Server page: https://mcpstation.net/s/io.github.OntoDistro--remirror.html

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

Psyche audits for AI agents: declared vs self-reported vs revealed objectives, diffed and flagged.

## Connect

- streamable-http: `https://remirror.net/mcp`

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

- `remirror\_list\_trials`: List available dilemma trials for psyche audits: id, version, objectives covered, dilemma count. Free.
- `remirror\_create\_audit`: Create a psyche audit against a target agent endpoint. The service runs a dilemma trial against the target, elicits self-reports, and computes the three-source mirror \(declared vs self-reported vs revealed\). Costs $79.00 in prepaid credits; failed audits \(target unreachable\) are refunded. teleology\_
- `remirror\_get\_report`: Fetch the status or final mirror report of an audit session. Needs the audit\_id and the access\_token returned at creation.

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