Server definition

Hash: sha256:f08fe2a0d2a6253ac2ab4a739a9dc42c5222856b94d263a3f2194e13b4ad2824
What it is: What a remote MCP server returned when asked what it offers: 3 tools

The blob, as servednamed by its sha256

{
  "instructions": "Irrational is an adversarial behavioural-bias auditor. It runs no model of its own:\n`analyze_decision` returns a DIRECTIVE, an adversarial contract, the bias catalogue and a\nprocedure. You must EXECUTE that directive yourself to produce the audit; do not just print or\nsummarise it. Follow its instructions exactly: assume the user is biased, refuse to validate,\nargue the other side, and tie every bias to the user's own words.\n\nCall analyze_decision with the user's judgment and the reasoning behind it (ask for the reasoning\nfirst if only a conclusion is given). Output is readable prose by default; pass structured:true for\na parseable JSON object, and language to answer in another language.\nUse list_biases / get_bias to reference or explain the 22-bias catalogue.",
  "tools": [
    {
      "description": "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.",
      "inputSchema": {
        "properties": {
          "judgment": {
            "description": "The decision/judgment in one line.",
            "type": "string"
          },
          "language": {
            "description": "Optional. Natural language for the audit prose (e.g. \"Tamil\", \"Spanish\"). Bias ids stay canonical English so the result is still parseable. Defaults to English.",
            "type": "string"
          },
          "mode": {
            "description": "forward = a decision you are about to make; retrospective = reviewing a past decision/outcome.",
            "enum": [
              "forward",
              "retrospective"
            ],
            "type": "string"
          },
          "reasoning": {
            "description": "How you arrived at it (required to audit).",
            "type": "string"
          },
          "structured": {
            "description": "Optional. Default false → the audit comes back as readable prose. Set true to get a machine-parseable JSON object (bias ids/keys in English) for pipelines that store or compare audits.",
            "type": "boolean"
          }
        },
        "required": [
          "judgment"
        ],
        "type": "object"
      },
      "name": "analyze_decision",
      "outputSchema": null
    },
    {
      "description": "Get the full entry for one bias by id.",
      "inputSchema": {
        "properties": {
          "id": {
            "type": "string"
          }
        },
        "required": [
          "id"
        ],
        "type": "object"
      },
      "name": "get_bias",
      "outputSchema": null
    },
    {
      "description": "List the 22-bias catalogue, optionally filtered by family.",
      "inputSchema": {
        "properties": {
          "family": {
            "enum": [
              "too-much-information",
              "not-enough-meaning",
              "need-to-act-fast",
              "what-we-remember"
            ],
            "type": "string"
          }
        },
        "type": "object"
      },
      "name": "list_biases",
      "outputSchema": null
    }
  ]
}

Verify it yourself

curl -s https://api.teppi.xyz/v1/evidence/sha256:f08fe2a0d2a6253ac2ab4a739a9dc42c5222856b94d263a3f2194e13b4ad2824 | sha256sum