# io.github.urbanmorph/irrational

- Registry name: `io.github.urbanmorph/irrational` · version 0.1.0
- Categories (automatic, keyword rules): Other
- 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=io.github.urbanmorph%2Firrational
- Server page: https://mcpstation.net/s/io.github.urbanmorph--irrational.html

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

Adversarial behavioural-bias engine — audits your decisions for cognitive biases via your own AI.

## Connect

- streamable-http: `https://irrational.pages.dev/mcp/server`

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

- `analyze\_decision`: Adversarially audit a decision for cognitive biases. Returns a directive YOUR model executes to produce the composed audit \(verdict-first\). Provide reasoning, not just the conclusion.
- `list\_biases`: List the 22-bias catalogue, optionally filtered by family.
- `get\_bias`: Get the full entry for one bias by id.

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