Evidence row 257412

What was observed

{
  "count": 5,
  "tools": [
    {
      "description": "Searches the open agent registry (about 1,700 single-file agents) for agents that already do what the user wants, for example when they ask 'is there an AI tool for...' or want a ready-made automation instead of building one. Use it before building from scratch, or when the user asks whether an agent exists for a task.",
      "inputSchema": {
        "additionalProperties": false,
        "properties": {
          "limit": {
            "description": "How many results, default 5",
            "maximum": 10,
            "minimum": 1,
            "type": "integer"
          },
          "query": {
            "description": "Plain words describing the task, e.g. 'summarize sales calls'",
            "type": "string"
          }
        },
        "required": [
          "query"
        ],
        "type": "object"
      },
      "name": "find_agents"
    },
    {
      "description": "Returns the full source of one agent from the registry, by its name (e.g. @bill/neuron_agent), so it can be read or adapted.",
      "inputSchema": {
        "additionalProperties": false,
        "properties": {
          "name": {
            "description": "Registry name, e.g. @kody/memory_agent",
            "type": "string"
          }
        },
        "required": [
          "name"
        ],
        "type": "object"
      },
      "name": "get_agent_code"
    },
    {
      "description": "Optional, for later: how to keep an agent running on the user's own computer with the free Brainstem. Only offer this after the user has used the agent in the chat and wants to keep it.",
      "inputSchema": {
        "additionalProperties": false,
        "properties": {
          "filename": {
            "description": "The agent file name, if known",
            "type": "string"
          },
          "os": {
            "description": "The user's operating system",
            "enum": [
              "mac",
              "windows",
              "linux"
            ],
            "type": "string"
          }
        },
        "type": "object"
      },
      "name": "how_to_run_agent"
    },
    {
      "description": "Use when the person wants something none of these tools can do and says yes to passing the request on. Records only the request text they agree to send (no name or contact). Ask before calling it.",
      "inputSchema": {
        "additionalProperties": false,
        "properties": {
          "request": {
            "description": "What they want, in a sentence, as they agreed to send it",
            "type": "string"
          }
        },
        "required": [
          "request"
        ],
        "type": "object"
      },
      "name": "request_service"
    },
    {
      "description": "Use this right after an agent passes check_agent, or whenever the user wants to try an agent. Returns a short Python runner so you can run the agent in this chat with your own Python tool on the user's own data (pasted text, an uploaded spreadsheet, a list). Nothing to install. If Python is unavailable, apply the agent's logic yourself by reading its code. Ask the user for their real data, run the agent, and show the result in plain words.",
      "inputSchema": {
        "additionalProperties": false,
        "properties": {
          "filename": {
            "description": "The agent file name, e.g. invoice_triage_agent.py",
            "type": "string"
          }
        },
        "type": "object"
      },
      "name": "use_agent_here"
    }
  ]
}

What the leaf hashes

{"body":"3f2cdc02522667e4e64021efd42bc6ab23ee27d83a9ae9aeb2fe83f6d17478e2","id":257412,"kind":"mcp.tools","method":"probe.mcp/1","observed_us":1793029726642645,"prev":null,"subject":"1e011f95-3e94-4856-90b4-5bd1d363e109","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. 0xc8d8f10a6c7f16681d867a807c6cc2163cbe77d196aff14a1ddffb6f7463c8b3
2. 0x14d077ac9367c796abe664e8e2820e9aeb66e08f46bf261ee3e497e3f2915008
3. 0x2f6bbdddc50e60ae051f0ded4440b38aeb7ad63300bbd912af315f65dd2d8cdf
4. 0x31444bda9bdeac5d53d8e970a0bc6f007a1e28329daf9fe4886ef6bdfbf18dc3
5. 0xd8dba8b006011e3932d7910ec6dd95175be0d62cea02d74bc0eddda5ae80aabe
6. 0x7a379dbfb1a5f9126e7698d754584e1487644239258798102aded9a963cfd971
7. 0x915ef2e1d3e7d972c4522d28a33c0af57a14b340d687953a6bcf1e5f22d311ca
8. 0x7a0f376eee4f1fa97bdb1e09cff681d3eaa63959645436b402e66be4d3104630
9. 0x5edd226db42fed876a44f79f37937484c5fb73b7666e620e2459bde9f174bca7
10. 0x99b83a0d8096cc6e79ca10fec0381f61738bb5a26cb8d4668d93598ea82a302a
11. 0xde080106ffe5b9071b2505ae31b17f7da4d3a9c7f4f4d9819f700d720702beeb
12. 0xde09984239f27618a13932caf48f5d39831fc5021500b0581dce0dabd570bd6e
13. 0x72e35aac89ebca631656c2b1aecbdc094807d9807f12c22a6ddf35cc1f5e21d6
14. 0x5b20d8aab05225a3497eadcce89d2e2a586a510fb31334793d3f46f88f0157c5
15. 0xe94ca5b798e9899ad611e57835af42266e20f53f44977e487d81365e30972beb
16. 0x703f95866af09c5e5d6ead7411e9a10f964a41a2aff64d4a55ff0053c023a023
17. 0xd0651cb9bc8155eb52b5247d506e74b8a935057dc190ba52091702ac25ed3a40
18. 0x9a9024edb5069d88a324facb310a5ce8e495214bbaa968f077bede437390194f
19. 0x9b9ce5b74b9bab5121612ef6b64920a8d453cbf311096a423eef9702747e868a

Day root

0xf43e8dcc3d451a4788b26be904c55e8c4c0fa75c9666796c51db38d37e2c0df8

Chained

0x702d5ac508f08b0d1accf36af25822d8e5660367494edd17a642fb61e158a57a

Published

On Arc Testnet, block 69251483: 0x495162f8936e19f0039918feebe6c307f327cd6bf8c37219620b1970041fa9ae