Evidence row 290633

What was observed

{
  "count": 3,
  "tools": [
    {
      "description": "Universal search tool supporting all SerpApi engines and result types.\n\n    When to use:\n        - Any query needing live, structured SERP data: web results, news, product listings, job postings, local businesses, flight/hotel prices, video results, images, stock/weather cards, knowledge graph entities.\n    \n    Engine discovery via MCP resources:\n        - serpapi://engines lists all engines supported by this tool.\n        - serpapi://engines/<engine> provides engine-specific parameters and supported options.\n        - Example: serpapi://engines/google_news\n\n    Input schema:\n        params: JSON object containing SerpApi engine parameters.\n            Common parameters:\n                - q: Search query. Required for most engines.\n                - engine: SerpApi engine name. Defaults to \"google_light\".\n                - location: Optional geographic location for localized results.\n                - output: Optional response format. Omit for JSON (default), or set to \"md\" for Markdown.\n    \n            Engine-specific parameters are available via MCP resources:\n                - serpapi://engines lists all supported engines.\n                - serpapi://engines/<engine> provides parameters and options for one engine.\n    \n        mode: Response mode. Defaults to \"complete\".\n            - \"complete\": Return the full SerpApi response.\n            - \"compact\": Remove metadata fields from JSON responses. Markdown is returned unchanged.\n    \n    Output schema:\n        structuredContent.result contains the response string: serialized JSON or unchanged Markdown.\n        The same string is included in text content. Tool failures preserve this wrapper and set isError to true.\n\n    Guided search:\n        Searches can request missing engine parameters from supporting clients using the engine catalog and engine-specific rules.\n        Flights collect airports and dates, hotels collect the destination and stay dates, and directions collect missing endpoints.\n        Other clients receive a missing-parameter error. Cancellation does not run a search.\n\n    Examples:\n        Weather: {\"params\": {\"q\": \"weather in London\", \"engine\": \"google\"}, \"mode\": \"complete\"}\n        Stock: {\"params\": {\"q\": \"AAPL stock\", \"engine\": \"google\"}, \"mode\": \"complete\"}\n        General: {\"params\": {\"q\": \"coffee shops\", \"engine\": \"google_light\", \"location\": \"Austin, TX\"}, \"mode\": \"complete\"}\n        Compact: {\"params\": {\"q\": \"news\"}, \"mode\": \"compact\"}\n        Markdown: {\"params\": {\"q\": \"news\", \"output\": \"md\"}}\n\n    Supported engines include (not limited to):\n        - google\n        - google_light\n        - google_flights\n        - google_hotels\n        - google_images\n        - google_news\n        - google_local\n        - google_shopping\n        - google_jobs\n        - bing\n        - yahoo\n        - duckduckgo\n        - youtube_search\n        - baidu\n        - ebay\n    ",
      "inputSchema": {
        "additionalProperties": false,
        "properties": {
          "mode": {
            "default": "complete",
            "description": "Response mode (default: \"complete\")\n- \"complete\": Returns the full response\n- \"compact\": Removes metadata fields from JSON responses; Markdown is unchanged",
            "type": "string"
          },
          "params": {
            "anyOf": [
              {
                "additionalProperties": true,
                "type": "object"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "description": "Dictionary of SerpApi engine-specific parameters. Common parameters include:\n- q: Search query (required for most engines)\n- engine: Search engine to use (default: \"google_light\")\n- location: Geographic location filter\n- output: Response format; omit for JSON or set to \"md\" for Markdown"
          }
        },
        "type": "object"
      },
      "name": "search"
    },
    {
      "description": "Interactive dashboard variant of `search`: returns summary metrics, a source breakdown chart, and a results table with a click-to-expand detail panel, all rendered in the conversation. Same params as `search`. Use for a richer visual overview of a query's results. Automatically selects an engine-specific dashboard when available (e.g. google_flights gets price intelligence charting).",
      "inputSchema": {
        "additionalProperties": false,
        "properties": {
          "params": {
            "additionalProperties": true,
            "default": null,
            "type": "object"
          }
        },
        "type": "object"
      },
      "name": "search_dashboard"
    },
    {
      "description": "Interactive UI variant of `search`: returns organic results as a sortable, searchable table rendered in the conversation. Same params as `search`. Use when the host supports MCP Apps and the user wants to browse results visually rather than read JSON.",
      "inputSchema": {
        "additionalProperties": false,
        "properties": {
          "params": {
            "additionalProperties": true,
            "default": null,
            "type": "object"
          }
        },
        "type": "object"
      },
      "name": "search_table"
    }
  ]
}

What the leaf hashes

{"body":"819928a64810edb94f8f001d220fec0b35e5cfc4cd1fdfb2a71c787ad9f63ef7","id":290633,"kind":"mcp.tools","method":"probe.mcp/1","observed_us":1793047452754375,"prev":null,"subject":"e360e7cb-719a-4b3d-972a-dce9dc4254c6","subject_kind":"endpoint"}

Proof

Fold these into the leaf in order, hashing each sorted pair with keccak256, to reach the root of 2026-10-26 (296695 rows).

1. 0xd6d43f32369383f18cb77506b8f22ff1c16ed0a19d5c3adb214047837220c353
2. 0xa9555d53d909e2ca5e5ff58a3660863c66a984082bab660b3cb472cc8aea4d68
3. 0x65742dbb28ebae2bb4ae86c86c49b44dbbee335003d29993fd6f7a9f12867872
4. 0x84e2dfff550a8cf10536f3d3bd9f1fa9ceff77daef9234d5f1c9d1d1843b71ec
5. 0x9418fd66ccd8955fffd9c51da7a8a29b6c7d75a02b13fb5e0d14e533bad89833
6. 0x245451f06c94dd720063d292518c18907547366713138ea181a7e142e2555086
7. 0xbbf248486d2a009d9b971cf3725c9292d17e46ac1e95f71a3c5eba6e385615b0
8. 0x17c9fc37c2dae1c12f78a16ce4bcc248b995e2966f612e7e9304304ce3e9844a
9. 0xda40352f4c3e9bb16eb1be95235380e545a169dcbe4a5adb1d4681bd81972196
10. 0x206287918135573a87e376ef5dd28f3e452e64e037a8e2c8a8f5db3f0e0e7d4c
11. 0x681ef979e2591e4ee00c2230855c75508aa926b1abc5e4e5e6a9348a15261045
12. 0x39d84ffb833c94bfff15760ea7da987f5303e407884de386d5a33b2328c7d785
13. 0x3199db04c2c73c3483386a86bf503eafde5af103465608156e2e5f42e72a6fbe
14. 0x6b927d53caa5125cdba9255612d524976c691f8672796c3f0885ba2c5b3af1ad
15. 0x6dc40f983a3840a0ad927a9ca17f4ff1e3b649a6c735e2a09b140db7c2caf13b
16. 0x703f95866af09c5e5d6ead7411e9a10f964a41a2aff64d4a55ff0053c023a023
17. 0xd0651cb9bc8155eb52b5247d506e74b8a935057dc190ba52091702ac25ed3a40
18. 0x9a9024edb5069d88a324facb310a5ce8e495214bbaa968f077bede437390194f
19. 0x9b9ce5b74b9bab5121612ef6b64920a8d453cbf311096a423eef9702747e868a

Day root

0xf43e8dcc3d451a4788b26be904c55e8c4c0fa75c9666796c51db38d37e2c0df8

Chained

0x702d5ac508f08b0d1accf36af25822d8e5660367494edd17a642fb61e158a57a

Published

On Arc Testnet, block 69251483: 0x495162f8936e19f0039918feebe6c307f327cd6bf8c37219620b1970041fa9ae