Irrational
Server Details
Adversarial behavioural-bias engine: audits your decisions for cognitive biases via your own AI.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2024-11-05
- URL
- Repository
- urbanmorph/irrational
- GitHub Stars
- 0
- Server Listing
- Irrational
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 3 tools
Each tool has a clearly distinct role: analyze_decision audits user reasoning, get_bias retrieves a single entry by id, and list_biases enumerates the catalogue. There is no overlap in purpose or selection ambiguity.
All three tools follow a consistent verb_noun snake_case pattern (analyze_decision, get_bias, list_biases). The verbs are standard CRUD-style conventions used predictably.
Three tools is on the thin side but each earns its place for a narrow bias-catalogue domain: enumerate, retrieve, and apply. No bloat or redundancy, though a fourth operation (e.g. search) might be warranted.
The core lifecycle is covered: listing the catalogue, fetching one entry, and performing the flagship audit. Minor gaps exist—no keyword search and no way to dump full catalogue content in one call—but agents can work around these with list plus get.
Available Tools
3 toolsanalyze_decisionARead-onlyIdempotentInspect
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.
Inputs: judgment (required), mode, language, reasoning, +1 more.
list_biasesARead-onlyIdempotentInspect
List the 22-bias catalogue, optionally filtered by family.
Inputs: family.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Psyche audits for AI agents: declared vs self-reported vs revealed objectives, diffed and flagged.
Trust gate for AI agents: multi-model adversarial consensus, signed and verifiable verdicts.
Evidence-weighted decision engines: AI business cases, venture readiness, free soundchecks.
Autonomous Decision Intelligence for evaluating economic decisions before value is committed.
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceEnables AI agents to test load-bearing assumptions through an evidence-driven pipeline, detect sycophancy and causal errors, calibrate confidence, and route decisions to act, revise, or halt.28 PyPIMIT
- AlicenseNot gradedqualityDmaintenanceEnables deep reasoning and cognitive enhancement through multi-agent debate, bias detection, and structured thinking, with privacy-first local execution.1MIT
- AlicenseAqualityCmaintenanceAdversarial AI review API — independent AI reviews another AI's output. Stop LLMs from grading their own homework. Provides automated quality assurance for AI-generated code, content, and other outputs through independent review pipelines.45 npm3MIT
- AlicenseNot gradedqualityNot gradedmaintenanceEnables users to coordinate multiple specialized personas to debate high-stakes decisions and aggregate their input into an explainable consensus with dissenting minority logs.MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.