Irrational MCP server
Commit Nov 15, 2026Audits decisions for cognitive biases by providing an adversarial framework and a 22-bias catalogue for AI agents to challenge reasoning.
Also known as urbanmorph/irrational
- Stars
- 0
- Tools
- —
- Downloads, 30 days
- —
- Latest version
- 0.1.1
- Last commit
- Nov 15, 2026
- License
- MIT
What is Irrational MCP?
Irrational audits decisions for cognitive biases by providing an adversarial framework and a 22-bias catalogue for AI agents to challenge reasoning.
Summary generated from the project's README
About Irrational MCP server
Irrational provides an adversarial framework designed to audit decisions for cognitive biases. It functions as a behavioral engine that an AI agent can use to challenge its own reasoning or a user's input. Instead of running its own language model, the server provides a structured contract that forces an agent to assume bias and argue the opposing side. This approach helps prevent the tendency of models to simply agree with the user.
Developers can connect to the server via a remote HTTP endpoint without needing to install local files or manage API keys. The system is stateless and does not store any decisions. It offers specific tools including analyze_decision for conducting audits, list_biases to view the catalogue, and get_bias for detailed information. The server includes a curated catalogue of 22 biases, each grounded in verified citations.
Users can integrate this into any MCP client by pointing to the live URL. The service is built as a dependency-free JSON-RPC endpoint. It is particularly useful for those who want to add a layer of critical thinking to their existing AI workflows without providing sensitive data to a third-party model.
What you can do with it
- 1Audit project planning decisionsAsk the agent to check a software rewrite proposal for errors like the planning fallacy or sunk cost bias.
- 2Challenge AI reasoning patternsUse the adversarial framework to force an AI to argue against its own initial conclusions.
- 3Browse a bias catalogueRetrieve a list of specific cognitive biases to understand how they might affect a particular thought process.
Written from the project's README. Every use case is checked against a quote from it.
How to install Irrational MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall Irrational MCP in Claude Code
$ claude mcp add irrational -- npx -y irrationalInstall Irrational MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"irrational": {
"command": "npx",
"args": [
"-y",
"irrational"
]
}
}
}Install Irrational MCP in VS Code
.vscode/mcp.json
{
"servers": {
"irrational": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"irrational"
]
}
}
}Install Irrational MCP in VS Code CLI
$ code --add-mcp '{"name":"irrational","type":"stdio","command":"npx","args":["-y","irrational"]}'Install Irrational MCP in Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"irrational": {
"command": "npx",
"args": [
"-y",
"irrational"
]
}
}
}Install Irrational MCP in Codex
$ codex mcp add irrational -- npx -y irrationalInstall Irrational MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.irrational] command = "npx" args = ["-y", "irrational"]
Install Irrational MCP in Gemini CLI
$ gemini mcp add -s user irrational npx -- -y irrationalInstall Irrational MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"irrational": {
"command": "npx",
"args": [
"-y",
"irrational"
]
}
}
}Automated checks
Ran Nov 15, 2026Full report →Not verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work · What to fix for more points
- Source repository linked and reachableurbanmorph/irrational is public and reachablegithub.com/urbanmorph/irrational ↗Pass
- Package names this repository as its sourceNot checked
- Build provenance (Sigstore attestation)Not checked
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-10-23github.com/urbanmorph/irrational ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNot checked
- No critical advisory in the package or its dependenciesNot checked
- No hidden instructions to the model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNot checked
- Remote endpoint answers the MCP handshakeinitialize answered with protocol 2024-11-05 in 74 msPass
README
View on GitHubIrrational
A field guide to the mistakes your mind makes, and an open, adversarial behavioural-bias engine you can call from your own AI or any MCP agent.
→ irrational.pages.dev · Field guide · Connect via MCP · Sources
Irrational runs no AI model. It provides the curated adversarial framework, a 22-bias catalogue, and a stateless scaffold, delivered as a public field guide and an open MCP tool, and the reasoning is done by whatever model you or your agent already have. No API keys. No stored decisions. Nothing leaves you.
A frontier model already knows the biases, so the value isn't informational; it's behavioural. A plain LLM is trained to agree, while Irrational has a fixed adversarial contract (assume you're biased, refuse to validate, argue the other side) that an agent can invoke systematically, even on its own draft reasoning.
What an audit looks like
You: "We should rewrite our 6-year-old backend from scratch this year, we've already spent two months on a POC that went well, and I'm confident we can finish in six."
THE CALL: Don't greenlight the big-bang rewrite. Carve off the worst module first, with a hard 3-month checkpoint. Confidence the 6-month plan succeeds: ~25%, mostly sunk cost + the planning fallacy.
THE AUDIT: Those "two months on a POC" are gone either way, but they're doing most of the talking (sunk cost). "About six months" is a best-case with no reference class; rewrites of mature systems routinely run 2–3× (planning fallacy)…
Verdict-first, every bias tied to your own words, grounded in a cited catalogue. See the full worked examples →
Add it to your AI
Listed on the official MCP Registry as io.github.urbanmorph/irrational. Connect any MCP client to the live endpoint, no install, no keys:
# Claude Code
claude mcp add --transport http irrational https://irrational.pages.dev/mcp/server
…or point any MCP client at https://irrational.pages.dev/mcp/server:
{
"mcpServers": {
"irrational": {
"type": "http",
"url": "https://irrational.pages.dev/mcp/server"
}
}
}
Tools: analyze_decision (the adversarial audit) · list_biases · get_bias. Pass language for a reply in another language, or structured: true for parseable JSON.
What's inside
- Field guide: 22 cognitive biases grouped by Buster Benson's four problems the brain solves, each with the question that breaks its spell and a verified citation.
- The engine: an MCP server exposing
analyze_decision,list_biases,get_bias.analyze_decisionreturns a verdict-first directive your model executes. The discipline is ours; the reasoning is yours. - The web forge: type a decision; it assembles the adversarial prompt in your browser and hands off to your AI. No model runs here.
- Pen-and-paper audit: the whole method on one printable page.
Stack
Astro (pure static) · Cloudflare Pages · a hand-rolled, dependency-free JSON-RPC MCP endpoint as a Pages Function. No runtime model, no database. Single source of truth: src/data/biases.ts feeds both the web and the MCP.
Develop
npm install --ignore-scripts # we don't use image optimization, so skip sharp's native build
npm run dev # http://localhost:4321
npm test # vitest, engine + catalogue (29 tests)
npm run build # static pages
The MCP endpoint is a Cloudflare Pages Function, run it locally with npx wrangler pages dev dist.
Contributing
Translations, proposed biases, and worked examples are welcome, see CONTRIBUTING.md. This project also publishes a public PDGI scorecard.
Licence
Code is MIT. The bias-catalogue text (definitions, examples, and the curated prose in src/data/) is additionally available under CC-BY-4.0. Every claim is cited, see /sources.
Built by Urban Morph.
Irrational MCP questions
How do I add Irrational MCP to Claude Code?
Run claude mcp add irrational -- npx -y irrational in your terminal. Add --scope user to make it available in every project.
How do I add Irrational MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
Does Irrational run its own AI model?
No, Irrational does not run any AI model; it provides the adversarial framework and the reasoning is performed by your existing AI model.
Do I need to provide an API key to use this?
No, the server requires no API keys and does not store any decisions.