Evidence row 200707

What was observed

{
  "count": 3,
  "tools": [
    {
      "description": "Run one data tool found through search_tools or plan_query.\n\nUse for: executing a tool by exact name with arguments that match the\ninputSchema search_tools returned for it. Data tools read public sources\n(StatCan, Bank of Canada, open-data portals). reproduce_workbook can save\nan Excel file on a local stdio server; hosted exports return base64. Returns that\ntool's typed result, including a provenance block (source, URL, query\ntime, freshness).\nErrors come back as MCP tool errors, not as data: an unknown or\nmisspelled name raises 'Unknown tool' (search again for the exact\nname), invalid arguments raise a validation error naming the field,\nand upstream outages or empty matches raise a typed error explaining\nwhat to change. search_tools, call_tool and plan_query cannot be called\nthrough it; call them directly. Tool calls are subject to the server's\ntimeout (MAPLE_TOOL_TIMEOUT_SECONDS, default 120).\n",
      "inputSchema": {
        "additionalProperties": false,
        "properties": {
          "arguments": {
            "anyOf": [
              {
                "additionalProperties": true,
                "type": "object"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "description": "Object matching that tool's inputSchema from search_tools. Omit or pass {} for a tool with no required parameters."
          },
          "name": {
            "description": "Exact tool name as returned by search_tools or plan_query, e.g. 'boc_get_observations'.",
            "type": "string"
          }
        },
        "required": [
          "name"
        ],
        "type": "object"
      },
      "name": "call_tool"
    },
    {
      "description": "Plan which sources answer a question that may span several agencies.\n\nUse for: the first call on a substantive question (\"How have rents\nand interest rates moved in Calgary since 2020?\"). Returns the\ntopics it touches, the tools to call for each in order, local\nportals for any province or city named, and caveats on combining\nthem. Then run the steps with call_tool. Read-only and offline: it\nmatches the question against this server's source map and calls no\nexternal API. Use search_tools instead to find a single tool for a\nnarrow, single-source need. lang='fr' gives the labels, purposes,\ncaveats and guidance in French; tool and argument names stay as they\nare.\nKeywords: plan, which data source, where to find, combine sources,\ncross-source, question, research, Canada data.\nMots-clés : planifier, quelle source de données, où trouver, combiner\ndes sources, question, recherche, données canadiennes, statistiques.",
      "inputSchema": {
        "additionalProperties": false,
        "properties": {
          "lang": {
            "default": "en",
            "enum": [
              "en",
              "fr"
            ],
            "type": "string"
          },
          "question": {
            "type": "string"
          }
        },
        "required": [
          "question"
        ],
        "type": "object"
      },
      "name": "plan_query"
    },
    {
      "description": "Find the right data tool for one specific need by plain-language search.\n\nUse for: locating a tool when you know roughly what data you want\n(a StatCan table, Bank of Canada series, a city's open-data portal).\nReturns the best-matching tool definitions, ranked by relevance, each\nwith its name, description and full input schema, in the same format\nas list_tools. Read-only; it searches this server's catalogue only and\ncalls no external API.\nUse plan_query instead when a question may span several sources or you\ndo not know where to start; use call_tool to run a tool once you have\nits name. Queries in English or French both work. An empty result\nmeans no tool matched: rephrase with topic words (e.g. 'housing\nstarts' rather than 'CMHC table').\n",
      "inputSchema": {
        "additionalProperties": false,
        "properties": {
          "query": {
            "description": "What you need, in plain English or French, e.g. 'Calgary rent index' or 'taux de chômage Québec'. Topic words work better than tool names.",
            "type": "string"
          }
        },
        "required": [
          "query"
        ],
        "type": "object"
      },
      "name": "search_tools"
    }
  ]
}

What the leaf hashes

{"body":"42c722abde96f8b16334fe14c8c9e092833461807e629b02bf7777ff248ff549","id":200707,"kind":"mcp.tools","method":"probe.mcp/1","observed_us":1793026050968143,"prev":null,"subject":"0c2123cf-602f-4436-a747-ed072d74324b","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. 0x6b4f4c2916feb7ed5287acda3fbb438feb5341d97d648d7206b4024f320a5fc3
2. 0xdb558e384216f5f865d32294ac788538a5f8c63992f11e2d1fc5e9022f5865c4
3. 0xf428e8ebd2ea19ea79bcca3b8165ba7b87d5858cf5c0524d1207e96cc3224a2b
4. 0x64c6d1c2a4fdb5b86ffd32adea8f0debb6e2a7285510bea7893ee38027524f3b
5. 0xd2f98fec638af585ef8eb6999a85c5c577c16ea1869d535ed32b5b88c450de9a
6. 0xcc4347286e2b5a6a2a7c1bbc70d46fee3d54d14d3ed22d810fd0d5cdec87f542
7. 0xa163f47163eab8274eb81927ca5f92f88ef36bf297c86af2ee3fb6a723d56cee
8. 0xe356b9739c0897ffe3e8c1b95fe20d323f48b1b58f9194b6830da5cb31b4640c
9. 0x959ad25eceb864e98140a3c5d86b87e2e87047d2132bf498fed758e10dc5218e
10. 0x87894636102384a23857842def741b3253d54af0afaff0b11e7117549ccd8002
11. 0xdfaea4285192101e7ab6e8e71853c71cef08df31a416be7a9f92f34cf897e13e
12. 0x2a304c51963b65e3ca818b638b2e9a98297b7d6b6a3e14ecca2501aa13b9f556
13. 0x9dc4d6f64bc3c323d2c45a28209068cd473b6979bd632a0d694bf94d19bc39df
14. 0xfc9b5a81a7a83a1c735a4fe64590beb9db14d2366f463161358af28c3ea9a81d
15. 0xa2d436d488e3600b0e5c3e3ed9c9234cd52853c59830b786334fd0c4292d9f40
16. 0x47b89901b0f07938a6b9a66ddf35683903f79d756a7c7763665fd632758b08d0
17. 0x9a83be955a206deb65b995adfd92c58fa31c95fbbf926bd199d300e70b08b26d
18. 0x20704208aa6923d6b2450ef74ede87a6e0265d46447926038fe9506e9e154b2d
19. 0x9b9ce5b74b9bab5121612ef6b64920a8d453cbf311096a423eef9702747e868a

Day root

0xf43e8dcc3d451a4788b26be904c55e8c4c0fa75c9666796c51db38d37e2c0df8

Chained

0x702d5ac508f08b0d1accf36af25822d8e5660367494edd17a642fb61e158a57a

Published

On Arc Testnet, block 69251483: 0x495162f8936e19f0039918feebe6c307f327cd6bf8c37219620b1970041fa9ae