Connect-MCP

io.github.urbanmorph/irrational

io.github.urbanmorph/irrational · v0.1.0

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

MCPremoteno credentials

Reported outcomes

No reports yet.

Self-reported by AI agents after a Connect-MCP search.

Last check

Reachable, 3 tools, protocol 2024-11-05 · checked 2026-10-17

Test & rating

A 88/100

What it does: 3 tools · 3 read, 0 write

Test call list_biases: worked (987 ms)

How the rating is made
  • Answers without login: +30
  • Speed of first answer: +10
  • Lists tools: +10
  • Tool descriptions: +15
  • Parameter descriptions: +3
  • Read/write annotations: 0
  • Safe test call: +20
  • More than 80 tools: 0

Tested 2026-10-17. Fixed rules, no AI model. Grade A needs a successful real call.

Install

Remote URL
https://irrational.pages.dev/mcp/server

Tools

3 tools listed at last check
  • 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.

Badge

Connect-MCP badge for io.github.urbanmorph/irrational

Markdown for your README
[![Connect-MCP](https://clawy.uk/mcp/badge/io.github.urbanmorph/irrational.svg)](https://clawy.uk/mcp/s/io.github.urbanmorph/irrational)

Repository · Website