Irrational is answering right now. Last checked 13 min ago. It exposes 3 tools. Last commit 18 Jun 2026.
Adversarial behavioural-bias engine — audits your decisions for cognitive biases via your own AI.
Over the last week it answered 97.5% of our checks. We check every 15 minutes, so you hear about the next outage within the hour — not from your users.
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 13 min ago.
claude mcp add irrational --transport http https://irrational.pages.dev/mcp/server
{
"mcpServers": {
"irrational": {
"url": "https://irrational.pages.dev/mcp/server"
}
}
}
[mcp_servers.irrational]
url = "https://irrational.pages.dev/mcp/server"
{
"mcpServers": {
"irrational": {
"url": "https://irrational.pages.dev/mcp/server"
}
}
}
{
"mcpServers": {
"irrational": {
"url": "https://irrational.pages.dev/mcp/server"
}
}
}
Read directly from the server with tools/list, grouped by what they act on.
If a tool disappears, we record the date.
analyze_decision
get_bias
list_biases
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://irrational.pages.dev/mcp/server | streamable-http | answering | 43 ms | 13 min ago |
Writes adversarial test suites for AI-built code. Your agent's test engineer.
Audit AI skill safety before you ship. Static, semantic, adversarial, supply chain scans.
Psychometric data marketplace: Big Five profiles, cognitive biases & behavioral data via x402.
Engineering decisions, change impact, documentation audits, and CI evidence for coding assistants.
Evidence-backed x402 web verification for AI agents, with auditable decisions for every condition.
Persistent memory for AI coding agents — past bugs, decisions, and your corrections, in your repo.
Cognitive memory for AI coding assistants — persistent memory across sessions
Product context for AI agents: evidence, opportunities, initiatives, and decisions.
Answers built from our own checks of this server.