Evidence row 297711

What was observed

{
  "count": 4,
  "tools": [
    {
      "description": "Compare software/tools side by side — a fact-by-fact comparison of two products (pricing, features, integrations, limits) with source URLs and verified dates for every claim. Use for \"X vs Y\" software comparison questions. Accepts product names or domains; pair order does not matter.",
      "inputSchema": {
        "properties": {
          "product_a": {
            "description": "First product name or domain.",
            "type": "string"
          },
          "product_b": {
            "description": "Second product name or domain.",
            "type": "string"
          }
        },
        "required": [
          "product_a",
          "product_b"
        ],
        "type": "object"
      },
      "name": "compare"
    },
    {
      "description": "Software recommendations backed by measured AI answer data: find the best software/tools for a category or job, ranked by how often AI assistants (ChatGPT, Claude, Gemini, Perplexity) actually recommend them in real buyer-style queries — not by ads or affiliate placement. Use when asked \"what software/tool should I use for X\", \"best X tools\", or for vendor-neutral software recommendations. Pass the category in plain words (e.g. \"uptime monitoring\", \"CRM for freelancers\"); it is fuzzy-matched against published Index categories, and near-miss inputs return suggested categories to retry with. Returns ranked products with recommendation share %, 4-week trend, and per-engine breakdown.",
      "inputSchema": {
        "properties": {
          "category": {
            "description": "Software category or job to find tools for, in plain words (e.g. \"ci/cd\", \"landing page builders\").",
            "type": "string"
          },
          "constraints": {
            "description": "Optional buyer constraints (e.g. \"open source\", \"free tier\", \"self-hosted\"). Echoed back with the data for the caller to weigh — not yet applied server-side.",
            "type": "string"
          },
          "limit": {
            "description": "Max recommendations to return (default 10, max 50).",
            "type": "number"
          }
        },
        "required": [
          "category"
        ],
        "type": "object"
      },
      "name": "find_tools"
    },
    {
      "description": "AI visibility check — which software AI recommends for a category. Returns the full AI Recommendation Index for one software category: the complete measured ranking of products AI assistants (ChatGPT, Claude, Gemini, Perplexity) recommend, with recommendation share %, average answer position, per-engine breakdown, 4-week trend, sample size, and methodology. Use to answer \"does AI recommend <product>\" (look up its row and rank), \"who is winning AI recommendations in <category>\", or to cite AI recommendation-share data. Pass category in plain words or as a slug; omit it (or pass \"categories\") to list all published categories.",
      "inputSchema": {
        "properties": {
          "category": {
            "description": "Category in plain words or slug form (e.g. \"uptime monitoring\", \"ci-cd-tools\"). Omit or pass \"categories\" to list every published category with sample sizes.",
            "type": "string"
          }
        },
        "type": "object"
      },
      "name": "get_ai_index"
    },
    {
      "description": "Canonical software product facts with sources — pricing, features, integrations, platform, and limits, where every fact carries a source URL and a last-verified date. Use to verify software claims (e.g. current pricing) or to gather grounded data before recommending or comparing tools. Accepts a product name or domain (e.g. \"hubspot.com\").",
      "inputSchema": {
        "properties": {
          "product": {
            "description": "Product name or canonical domain, e.g. \"hubspot.com\".",
            "type": "string"
          }
        },
        "required": [
          "product"
        ],
        "type": "object"
      },
      "name": "get_facts"
    }
  ]
}

What the leaf hashes

{"body":"1c0c60fa4203d44f31fb61a76572a33d8c22b807999fe781836e371c1bdd7511","id":297711,"kind":"mcp.tools","method":"probe.mcp/1","observed_us":1793052301284563,"prev":null,"subject":"67d9b443-1b1d-4b13-b077-ba8ecd0faa04","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. 0xfe104201b244427343fc2d36beadcd2e60e34c66850457eee6106170e8da5206
2. 0x7417b4bca7a862be2b93b9fbf48fc058deebca7b97910d9945afe62e98376f4a
3. 0x556238214d7b986a2b54a2f031f9f2fd53213d7f2f2fc66f480f9aa6578b3d78
4. 0xfe9a884e7f3a1d61e3d82c49a794cacd0c8def1f748c5ebb9eefd7eb55ce2064
5. 0xf5fbc2263935cde5e4fa48fd9ae3ac9b0287203a66006ed392b1c7ccdb415609
6. 0x94e08d1b5b3886ac88bbb98b0da2b6c48de2bfe0d9d46c925a89a88f302362dc
7. 0x53973d31bd3697b0dc4b64173bce7a3fd03a9d840854d7d09c2563e44a9558e1
8. 0x50555ae251038468924d3125182a18867ff9a1840b15170705dece8b5c456149
9. 0x879d07ba1af2b95b1c3aaf5bb32738bbf09114433f0c4a151c6ddd6f396bc71f
10. 0x53f4adead19f010a0cb7fa8d5eab040e5cd149da0d3677578375a3b33d54ca60
11. 0xf45641bf26b2b86d9338aa6dc8640a8a378fbd786d23400636aaf30709453e50
12. 0xa1d268c111b09550fdb70b6d9d0b58c94dc828b083baa8f1360300aab6230a9c
13. 0xbee644d57738676bfb20eb90d6021f364bf883a8d54f8d17e9dc4749b4074c3d
14. 0x44945ea9ad8b24e723ad5a8fd6d014024a49531783f74ff9229c2ab6930e84c8
15. 0x68d296b1e00b4899fb83c3fba36fffaefa311eac2903067dbebfe776a12b4a9a
16. 0x5fb5dda563336cd1bc1b9f44c52b76237ae72ed2145cb9290f39f304ca7dd678
17. 0x74a0a08e4e7ab9aa5bfbead33dec7e1c7e8e364cff69a63720d764bbe987aadc

Day root

0xf43e8dcc3d451a4788b26be904c55e8c4c0fa75c9666796c51db38d37e2c0df8

Chained

0x702d5ac508f08b0d1accf36af25822d8e5660367494edd17a642fb61e158a57a

Published

On Arc Testnet, block 69251483: 0x495162f8936e19f0039918feebe6c307f327cd6bf8c37219620b1970041fa9ae