Evidence row 258186

What was observed

{
  "count": 4,
  "tools": [
    {
      "description": "Idempotent · 30s timeout · Automatically infer JSON Schema from sample data without extraction. Pass `idempotency_key` to deduplicate within 5 minutes.",
      "inputSchema": {
        "additionalProperties": false,
        "properties": {
          "idempotency_key": {
            "description": "Optional cache key (UUID/string) for 5-minute deduplication. Repeat calls with same key return cached inferred schema instantly.",
            "type": "string"
          },
          "sample_data": {
            "description": "Representative sample data as JSON string (array of objects or single object). Schema is inferred from structure; use first 1-10 rows for array samples. Max 200KB.",
            "examples": [
              "{\"product_id\":123,\"title\":\"Laptop Pro\",\"price\":1299.99,\"in_stock\":true}",
              "[{\"id\":1,\"email\":\"alice@example.com\",\"verified\":true},{\"id\":2,\"email\":\"bob@example.com\",\"verified\":false}]",
              "{\"name\":\"Report Q1\",\"sections\":[{\"title\":\"Sales\",\"value\":50000}]}"
            ],
            "type": "string"
          }
        },
        "required": [
          "sample_data"
        ],
        "type": "object"
      },
      "name": "auto_schema_learn"
    },
    {
      "description": "Idempotent · 30s timeout · Extract data from multiple sources (JSON/JSONL/text) with a single consistent schema. Pass `idempotency_key` to deduplicate within 5 minutes.",
      "inputSchema": {
        "additionalProperties": false,
        "properties": {
          "idempotency_key": {
            "description": "Optional deduplication key (UUID/string) for 5-minute cache. Identical batch calls (same sources + schema + key) return cached results instantly.",
            "type": "string"
          },
          "schema": {
            "description": "Optional target JSON Schema (draft-07) applied to all sources. If omitted, inferred from first source and reused across remaining sources. Enables consistent field extraction from diverse formats.",
            "type": "object"
          },
          "sources": {
            "description": "Array of 1-100 data sources to extract from. Each source includes type (format) and content (raw data).",
            "items": {
              "additionalProperties": false,
              "properties": {
                "content": {
                  "description": "Raw source content (max 200KB per source). For jsonl: each line must be valid JSON. For text: format \"key1:value1,key2:value2\".",
                  "type": "string"
                },
                "type": {
                  "description": "Source format: \"json\" (single object or array), \"jsonl\" (newline-delimited JSON objects), \"text\" (key:value pairs delimited by commas/semicolons)",
                  "enum": [
                    "json",
                    "jsonl",
                    "text"
                  ],
                  "type": "string"
                }
              },
              "required": [
                "type",
                "content"
              ],
              "type": "object"
            },
            "maxItems": 100,
            "minItems": 1,
            "type": "array"
          }
        },
        "required": [
          "sources"
        ],
        "type": "object"
      },
      "name": "batch_extract"
    },
    {
      "description": "Idempotent · 30s timeout · Extract structured data from API response JSON with schema adaptation. Pass `idempotency_key` to deduplicate within 5 minutes.",
      "inputSchema": {
        "additionalProperties": false,
        "properties": {
          "content": {
            "description": "API response body as raw JSON string (max 200KB). Can be single object, array of objects, or array of primitives. Automatically parsed and validated.",
            "examples": [
              "{\"id\":1,\"name\":\"Alice\",\"role\":\"admin\"}",
              "[{\"id\":1,\"name\":\"Alice\"},{\"id\":2,\"name\":\"Bob\"}]",
              "[{\"user\":{\"id\":1,\"name\":\"Alice\"},\"status\":\"active\"}]"
            ],
            "type": "string"
          },
          "idempotency_key": {
            "description": "Optional deduplication key (UUID or unique string) for 5-minute cache. Identical calls return cached result instantly.",
            "type": "string"
          },
          "schema": {
            "description": "Optional target JSON Schema (draft-07) for field extraction. If omitted, inferred from content structure. Enforces consistent field extraction across multiple API responses.",
            "type": "object"
          }
        },
        "required": [
          "content"
        ],
        "type": "object"
      },
      "name": "extract_from_api"
    },
    {
      "description": "Idempotent · 30s timeout · Extract structured data from URL content with auto schema learning. Pass `idempotency_key` to deduplicate identical calls within 5 minutes.",
      "inputSchema": {
        "additionalProperties": false,
        "properties": {
          "idempotency_key": {
            "description": "Optional UUID or unique identifier for 5-minute deduplication cache. Same key + tool = cached result in <5ms, zero re-fetching.",
            "type": "string"
          },
          "schema": {
            "description": "Optional pre-defined JSON Schema (draft-07). If omitted, schema is auto-inferred from content. Provide to enforce strict field extraction and type coercion.",
            "type": "object"
          },
          "url": {
            "description": "HTTP(S) URL to fetch (will auto-download and parse), or raw content string (up to 200KB). Max 200KB after fetch.",
            "examples": [
              "https://api.github.com/users/octocat",
              "https://example.com/page.html",
              "{\"name\":\"John Doe\",\"age\":30,\"email\":\"john@example.com\"}"
            ],
            "type": "string"
          }
        },
        "required": [
          "url"
        ],
        "type": "object"
      },
      "name": "extract_from_url"
    }
  ]
}

What the leaf hashes

{"body":"db518d5a1dcc90ed3a656966577190683e056e875303a3d8c6b714c06bd37078","id":258186,"kind":"mcp.tools","method":"probe.mcp/1","observed_us":1793029980345626,"prev":null,"subject":"c6dc9ff8-d951-4d0a-8a1e-d78cf870837b","subject_kind":"endpoint"}

Proof

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