Evidence row 265261

What was observed

{
  "count": 10,
  "tools": [
    {
      "description": "List the AI models available to the current user. Returns ID, provider, tier, context window, and capability flags (web search, vision, streaming). Use the IDs returned here as the `models` array argument to council_query / council_query_with_rag.",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "properties": {},
        "type": "object"
      },
      "name": "council_models"
    },
    {
      "description": "Send a prompt to a council of frontier AI models across 9 labs (Anthropic, OpenAI, Google, xAI, DeepSeek, Qwen, Mistral, Moonshot, z.ai). Returns each model's independent response plus a moderator-synthesized consensus answer with an agreement score and the key point of disagreement, when one exists. Use when a single-model answer might hallucinate or when verification across labs matters (research, contracts, architecture, legal, medical, code review). Adaptive-cost pattern: for a quick check, call with 2-3 models; if consensusScore comes back low (or keyDisagreement matters to the decision), escalate by re-running with more models — easy questions stay cheap, disputed ones get more compute. TIMEOUTS: a full council can run for minutes. If your MCP client has a fixed tool-call timeout, set async=true — you get a queryId back immediately and fetch the finished result with council_result. Call council_models first to pick specific model IDs, and council_usage to check remaining budget. Bills against the user's Council AI monthly budget.",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "additionalProperties": false,
        "properties": {
          "async": {
            "default": false,
            "description": "When true, return {queryId, status:\"running\"} immediately instead of waiting for the council. Fetch the finished result with council_result. Use whenever your MCP client enforces a fixed tool-call timeout (a full council typically runs 1-3 minutes) or when querying 4+ models.",
            "type": "boolean"
          },
          "mode": {
            "default": "independent",
            "description": "Cross-model visibility. 'independent' (default): all models answer in parallel, blind to each other — best for unbiased comparison; the synthesis reconciles them. 'sequential': models answer one at a time and each later model sees the earlier answers, debate-style — takes the SUM of per-model latencies instead of the max, so strongly consider async=true with it.",
            "enum": [
              "independent",
              "sequential"
            ],
            "type": "string"
          },
          "models": {
            "description": "Model IDs to include (2-10). Defaults to a cross-lab flagship council. Use council_models to list available IDs. Example: [\"claude-fable-5.1\", \"gpt-6.1-sol\", \"gemini-3.8-flash\"]",
            "items": {
              "type": "string"
            },
            "maxItems": 10,
            "minItems": 2,
            "type": "array"
          },
          "prompt": {
            "description": "The question or task to send to the council. Include all needed context — every query is stateless. Example: \"Is optimistic locking or a distributed lock the better fit for this checkout flow? [paste flow description]\"",
            "maxLength": 20000,
            "minLength": 1,
            "type": "string"
          },
          "synthesisDirective": {
            "description": "Optional instructions for the moderator that synthesizes the council's answers. The council models never see this — it only shapes the synthesis. Use for special modes, e.g. devil's advocate: \"Argue against the majority position — find the strongest case that the consensus is wrong and surface every dissenting point.\" Or output contracts: \"Answer VERDICT: SAFE/UNSAFE first, then justification.\" Omit for the standard balanced synthesis.",
            "maxLength": 8000,
            "minLength": 1,
            "type": "string"
          },
          "synthesize": {
            "default": true,
            "description": "When true (default), include the moderator synthesis + consensus score. Set false to get only the raw per-model responses (faster, cheaper).",
            "type": "boolean"
          }
        },
        "required": [
          "prompt"
        ],
        "type": "object"
      },
      "name": "council_query"
    },
    {
      "description": "Like council_query, but first retrieves the most relevant passages from the user's personal Council RAG library (uploaded PDFs, Word docs, contracts, research papers, codebases) and injects them into every model's prompt. Use when the question is about content the user has uploaded — contract review, research synthesis across a paper library, code review against an architecture doc, etc. Ultra-tier only.",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "additionalProperties": false,
        "properties": {
          "async": {
            "default": false,
            "description": "When true, retrieval runs immediately (sources are returned right away) but the council itself runs in the background — fetch the finished answer with council_result. Use when your MCP client enforces a fixed tool-call timeout or when querying 4+ models.",
            "type": "boolean"
          },
          "library_query": {
            "description": "Optional retrieval-specific query. If omitted, the main prompt is used as the retrieval query. Set this when the user's prompt has unrelated framing but the concrete documents to retrieve are described by something different.",
            "type": "string"
          },
          "models": {
            "description": "Model IDs to include. Defaults to the user's preferred council.",
            "items": {
              "type": "string"
            },
            "maxItems": 10,
            "minItems": 2,
            "type": "array"
          },
          "project_id": {
            "description": "Restrict retrieval to a specific Council project workspace.",
            "type": "string"
          },
          "prompt": {
            "description": "The question or task to send to the council. Example: \"Review this NDA draft against our standard playbook terms.\"",
            "maxLength": 20000,
            "minLength": 1,
            "type": "string"
          },
          "retrieval_limit": {
            "description": "Number of chunks to retrieve. Default: 8.",
            "maximum": 20,
            "minimum": 1,
            "type": "number"
          },
          "synthesize": {
            "default": true,
            "description": "When true (default), include the moderator synthesis + consensus score.",
            "type": "boolean"
          }
        },
        "required": [
          "prompt"
        ],
        "type": "object"
      },
      "name": "council_query_with_rag"
    },
    {
      "description": "Fetch the result of a council_query started with async=true. Returns status \"running\" while the council is still working (wait 30-60 seconds and call again), the full synthesis + per-model responses once complete, or status \"failed\" with the error. Polling is free — the council run itself was already billed by council_query.",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "additionalProperties": false,
        "properties": {
          "queryId": {
            "description": "The queryId returned by council_query when called with async=true.",
            "maxLength": 40,
            "minLength": 10,
            "type": "string"
          }
        },
        "required": [
          "queryId"
        ],
        "type": "object"
      },
      "name": "council_result"
    },
    {
      "description": "Multi-model code review. Sends a unified diff (or code snippet) to multiple frontier AI models from different labs in parallel, each acting as an independent reviewer with an explicit verdict + findings contract. Returns a verdict-first synthesis: overall SHIP/NO-SHIP, consensus score, confirmed findings (flagged by 2+ models), then dissents (single-model findings with reasoning), then each reviewer's verdict. Diffs are capped at 14,000 characters — split larger changes by file or hunk and call once per chunk. Bills against the user's Council AI monthly budget like any council query.",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "additionalProperties": false,
        "properties": {
          "async": {
            "default": false,
            "description": "When true, return {queryId, status:\"running\"} immediately and fetch the finished review with council_result. Use when your MCP client enforces a fixed tool-call timeout, or with 4+ reviewers — async runs also give slow reasoning models a much larger time budget before they are cut off.",
            "type": "boolean"
          },
          "context": {
            "description": "What the change is supposed to do: intent, constraints, related files or invariants reviewers cannot see from the diff alone. Improves signal, reduces false positives.",
            "maxLength": 3000,
            "type": "string"
          },
          "diff": {
            "description": "The unified diff (git diff output) or code snippet to review. Max 14,000 characters — if your diff is larger, split it by file or hunk and review each part separately. Example: the output of `git diff HEAD~1`.",
            "minLength": 1,
            "type": "string"
          },
          "focus": {
            "default": "all",
            "description": "Review focus: \"bugs\" (correctness), \"security\", \"performance\", \"architecture\", or \"all\" (default — full review, bugs prioritized).",
            "enum": [
              "bugs",
              "security",
              "performance",
              "architecture",
              "all"
            ],
            "type": "string"
          },
          "models": {
            "description": "Model IDs to include as reviewers (2-10). Defaults to the user's preferred council. Use council_models to list available IDs.",
            "items": {
              "type": "string"
            },
            "maxItems": 10,
            "minItems": 2,
            "type": "array"
          }
        },
        "required": [
          "diff"
        ],
        "type": "object"
      },
      "name": "council_review"
    },
    {
      "description": "Return the user's current monthly cost-budget consumption (current spend, budget cap, percentage used, days until reset). Use to decide whether to warn the user before invoking another council_query, or to suggest using cheaper models. Per Council's rule: never show dollar amounts to the user in the response — use percentages.",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "properties": {},
        "type": "object"
      },
      "name": "council_usage"
    },
    {
      "description": "Permanently delete a document from the user's Council RAG library — the record, every indexed chunk, AND the stored file are removed. This cannot be undone; re-adding the document requires uploading it again. Get document IDs from library_list. Use when the user asks to remove a document or when the 200-document library cap blocks an upload. Confirm with the user before deleting anything they did not explicitly name. No model call, no budget consumption.",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "additionalProperties": false,
        "properties": {
          "documentId": {
            "description": "ID of the document to delete, as returned by library_list or library_upload.",
            "minLength": 1,
            "type": "string"
          }
        },
        "required": [
          "documentId"
        ],
        "type": "object"
      },
      "name": "library_delete"
    },
    {
      "description": "List the documents in the user's Council RAG library. Returns id, filename, source type, ingestion status, chunk count, and upload date for each document. No retrieval, no budget consumption.",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "properties": {},
        "type": "object"
      },
      "name": "library_list"
    },
    {
      "description": "Semantic search over the user's Council RAG library (uploaded PDFs, Word docs, contracts, research papers, codebases). Returns top-K chunks with source filename and page number. No model call, no budget consumption. Use to find direct quotes, check what the library contains, or scope a follow-up council_query_with_rag call.",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "additionalProperties": false,
        "properties": {
          "limit": {
            "description": "Number of chunks to return, 1-20. Default: 8.",
            "maximum": 20,
            "minimum": 1,
            "type": "number"
          },
          "project_id": {
            "description": "Restrict retrieval to a specific Council project workspace ID. Omit to search the whole library.",
            "type": "string"
          },
          "query": {
            "description": "Semantic retrieval query — describe the content you want, not keywords. Example: \"termination and notice-period clauses in the vendor agreement\"",
            "maxLength": 2000,
            "minLength": 1,
            "type": "string"
          }
        },
        "required": [
          "query"
        ],
        "type": "object"
      },
      "name": "library_search"
    },
    {
      "description": "Upload a document into the user's Council RAG library so future council_query_with_rag and library_search calls can retrieve it. Accepts PDF, Word (docx), text, and markdown files as base64 — images are not supported. Max 10MB per file via MCP (the web library at https://council-ai.app/settings?tab=library takes up to 50MB); libraries hold up to 200 documents. Ingestion (chunking + embedding) runs in the background: the returned document starts in \"pending\" status — check library_list for it to reach \"ready\" before querying against it. No model call, no budget consumption.",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "additionalProperties": false,
        "properties": {
          "contentBase64": {
            "description": "The file's raw bytes, base64-encoded (standard alphabet, no data: URI prefix). For a plain-text or markdown document, base64-encode the UTF-8 text.",
            "minLength": 1,
            "type": "string"
          },
          "filename": {
            "description": "Original filename including extension — the extension drives type detection. Example: \"vendor-contract-2026.pdf\".",
            "maxLength": 512,
            "minLength": 1,
            "type": "string"
          },
          "mimeType": {
            "description": "MIME type, e.g. \"application/pdf\". Optional — the backend verifies the real type from the file's magic bytes regardless.",
            "maxLength": 255,
            "type": "string"
          },
          "projectId": {
            "description": "Council project workspace to file the document under. Omit for the general library.",
            "type": "string"
          },
          "tags": {
            "description": "Free-form tags to attach to the document, e.g. [\"contracts\", \"2026\"].",
            "items": {
              "type": "string"
            },
            "type": "array"
          }
        },
        "required": [
          "filename",
          "contentBase64"
        ],
        "type": "object"
      },
      "name": "library_upload"
    }
  ]
}

What the leaf hashes

{"body":"65df0374114eccbecefb10ae75acd65921881be438d900c1e4a751a05d85e85b","id":265261,"kind":"mcp.tools","method":"probe.mcp/1","observed_us":1793034688659155,"prev":null,"subject":"b8461b9e-6599-44c8-a158-248a011a37f6","subject_kind":"endpoint"}

Proof

Its day has not closed yet. A day closes ten minutes after midnight UTC; the proof appears here then.