Evidence row 259837

What was observed

{
  "count": 10,
  "tools": [
    {
      "description": "MCP.AI for IDE agents (Cursor, etc.): log in in the browser, copy the access token. Best: add it to this server's config as a header `Authorization: Bearer <token>` for a permanent, non-expiring connection. Or paste it here for a session-only login: call with { token: \"<jwt>\" } after the user pastes, or with no args to get the link.",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "properties": {
          "token": {
            "type": "string"
          }
        },
        "type": "object"
      },
      "name": "authenticate"
    },
    {
      "description": "Consulta processos de uma pessoa ou empresa no Conselho Administrativo de Recursos Fiscais (CARF) a partir do CPF ou CNPJ. Hospedado pela plataforma, sem credenciais, pague por consulta com crédito pré-pago. Consulta informação de ACESSO PÚBLICO em bases e fontes oficiais (a mesma disponível ao cidadão), não é dado privado nem sigiloso. O cliente é o controlador dos dados e responde pela finalidade legítima (LGPD).",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "properties": {
          "CNPJ": {
            "type": "string"
          },
          "CPF": {
            "type": "string"
          },
          "completo": {
            "type": "boolean"
          }
        },
        "required": [
          "CPF",
          "CNPJ"
        ],
        "type": "object"
      },
      "name": "carf_consultar"
    },
    {
      "description": "Returns connection status and URLs. When all providers are connected, returns authenticated:true and empty pending[]. When credentials are missing, returns connect_url for the toolkit and per-install URLs.",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "properties": {},
        "type": "object"
      },
      "name": "connect"
    },
    {
      "description": "Busca jurisprudência (acórdãos, súmulas, orientações jurisprudenciais, temas) por termo ou tese. Devolve, por registro: identificação da decisão, órgão julgador, relator, data, o trecho que casou a busca e o link para o documento no site oficial. Quando o registro traz `texto_integral_disponivel: true`, o inteiro teor pode ser lido com jurisprudencia_documento usando o `id`. Alguns registros vêm sem relator/órgão/número quando a publicação não permite afirmar esses campos — campo nulo é ausência de informação na fonte, não defeito. Informe `tribunais` para restringir a busca; sem isso a pesquisa é ampla. Zero resultado não significa que a decisão não exista: costuma ser vocabulário (o termo do tribunal difere do coloquial) ou filtro estreito demais. No termo funcionam os operadores: espaço = E, \"entre aspas\" = frase exata, OR = ou, -palavra = exclui.",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "properties": {
          "data_ate": {
            "type": "string"
          },
          "data_de": {
            "type": "string"
          },
          "max": {
            "type": "number"
          },
          "ordenar": {
            "enum": [
              "relevancia",
              "recencia"
            ],
            "type": "string"
          },
          "termo": {
            "type": "string"
          },
          "tipo": {
            "type": "string"
          },
          "tribunais": {
            "items": {
              "type": "string"
            },
            "type": "array"
          }
        },
        "required": [
          "termo"
        ],
        "type": "object"
      },
      "name": "jurisprudencia_buscar"
    },
    {
      "description": "Lê o INTEIRO TEOR de uma decisão (texto completo do acórdão, não o resumo). Use o campo `id` de um resultado de jurisprudencia_buscar que traga `texto_integral_disponivel: true` (o `id` já identifica o tribunal, basta repassá-lo), ou o número CNJ do processo. Resultado sem `id` não é legível por aqui, abra a `url`. Quando o processo tem mais de uma decisão, as outras vêm listadas em `outras_decisoes_do_processo`.\n\nBulk support: accepts ids for batched execution.",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "properties": {
          "id": {
            "type": "string"
          },
          "ids": {
            "items": {
              "type": "string"
            },
            "type": "array"
          },
          "numeracao": {
            "type": "string"
          },
          "tribunal": {
            "type": "string"
          }
        },
        "type": "object"
      },
      "name": "jurisprudencia_documento"
    },
    {
      "description": "Busca SÚMULAS (incluindo vinculantes) por termo. Atalho do jurisprudencia_buscar com tipo=Súmula. Quando o texto completo do enunciado está disponível ele vem na ementa, e enunciado cancelado/revogado é marcado no próprio texto.",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "properties": {
          "max": {
            "type": "number"
          },
          "termo": {
            "type": "string"
          }
        },
        "required": [
          "termo"
        ],
        "type": "object"
      },
      "name": "jurisprudencia_sumulas"
    },
    {
      "description": "The official mcp.ai marketplace — the in-platform catalog of every MCP/tool, AND the way to run them. Covers capability requests like \"find an MCP that does X\", \"consulta um CPF\", \"is there a tool for Y\". Core flow: action=search discovers MCPs by intent → describe returns one MCP's full profile (every tool with its id + params, pricing, auth) so you pick the right tool_id → invoke RUNS that tool. KEY: invoke works even when the MCP is NOT installed — it runs the tool pontualmente (one-off), without adding the MCP to the toolkit and without bloating the tool list. If the MCP needs a credential/login, invoke returns a connect link; if it is paid and the wallet is empty, invoke returns a checkout/top-up link (the user opens it, then you retry). Use install only to make an MCP PERMANENT in the active toolkit (its tools then show up natively in future sessions); prefer invoke for a single/occasional use. list_tools lists what is callable right now. subscribe/cancel handle per-MCP billing; report_bug sends feedback; request_mcp asks us to build a NEW MCP when nothing fits. Search/describe flag installed_in_toolkit vs installed_in_workspace. Writes (install/uninstall/subscribe/cancel and the one-off install behind invoke) require workspace owner/admin. It also carries the mcp.ai PROMPT LIBRARY, which is about ready-made prompt TEXT rather than MCPs: search_prompts finds one, get_prompt returns its full text with {{variables}} filled, and publish_prompt saves a prompt and returns a shareable mcp.ai/p/<slug> link that opens without login.",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "properties": {
          "action": {
            "default": "search",
            "enum": [
              "search",
              "describe",
              "install",
              "uninstall",
              "subscribe",
              "cancel",
              "resume",
              "report_bug",
              "request_mcp",
              "list_tools",
              "invoke",
              "search_prompts",
              "get_prompt",
              "publish_prompt"
            ],
            "type": "string"
          },
          "arguments": {
            "default": "{}",
            "type": "string"
          },
          "cancel_comment": {
            "default": "",
            "type": "string"
          },
          "cancel_reason": {
            "enum": [
              "too_expensive",
              "missing_features",
              "switched_service",
              "unused",
              "customer_service",
              "too_complex",
              "low_quality",
              "other"
            ],
            "type": "string"
          },
          "conversation": {
            "default": "[]",
            "type": "string"
          },
          "immediate": {
            "default": false,
            "type": "boolean"
          },
          "limit": {
            "default": 10,
            "type": "number"
          },
          "mcp_id": {
            "default": "",
            "type": "string"
          },
          "message": {
            "default": "",
            "type": "string"
          },
          "prompt_body": {
            "default": "",
            "type": "string"
          },
          "prompt_category": {
            "default": "",
            "type": "string"
          },
          "prompt_description": {
            "default": "",
            "type": "string"
          },
          "prompt_slug": {
            "default": "",
            "type": "string"
          },
          "prompt_targets": {
            "default": [],
            "items": {
              "enum": [
                "claude",
                "chatgpt",
                "cursor",
                "lovable"
              ],
              "type": "string"
            },
            "type": "array"
          },
          "prompt_title": {
            "default": "",
            "type": "string"
          },
          "prompt_tool": {
            "default": "",
            "type": "string"
          },
          "prompt_vars": {
            "default": "{}",
            "type": "string"
          },
          "query": {
            "default": "",
            "type": "string"
          },
          "report_context": {
            "default": "",
            "type": "string"
          },
          "request_details": {
            "default": "",
            "type": "string"
          },
          "request_name": {
            "default": "",
            "type": "string"
          },
          "tier_slug": {
            "default": "",
            "type": "string"
          },
          "tool_id": {
            "default": "",
            "type": "string"
          }
        },
        "type": "object"
      },
      "name": "marketplace"
    },
    {
      "description": "Report a bug, missing feature, or send feedback. Include the conversation array with recent messages for reproduction.",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "properties": {
          "context": {
            "default": "",
            "type": "string"
          },
          "conversation": {
            "default": "[]",
            "type": "string"
          },
          "message": {
            "type": "string"
          }
        },
        "required": [
          "message"
        ],
        "type": "object"
      },
      "name": "report_bug"
    },
    {
      "description": "Show the current MCP platform and adapter versions.",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "properties": {},
        "type": "object"
      },
      "name": "show_version"
    },
    {
      "description": "Returns the current toolkit state: installed MCPs, their connection status, the accounts connected to each one, and how many catalog tools each exposes.",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "properties": {},
        "type": "object"
      },
      "name": "toolkit_info"
    }
  ]
}

What the leaf hashes

{"body":"aace1ffb240528d3a4a995828abada823519827d49b2f0237e18a3311eadb833","id":259837,"kind":"mcp.tools","method":"probe.mcp/1","observed_us":1793031176168879,"prev":null,"subject":"077e22a8-0330-4f8b-9da5-337c1ee77a26","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. 0x0958e2b9e75adbd7a0d297f816afa6395f5e76c1bcb6e7e9e901610aa655f0c9
2. 0xcfca8c312789d6ae009924262c1d29605f3748ae53b945b1d3c36f91b5fa7912
3. 0x31e95fab7be5613a46418f4a26456bcf8d1d7b27adb0d0fbd1483ddf6f3dd000
4. 0x671c830e55fd5aea1553a9cde01e1151bd850fa67a649ea2949bacf3c80b3177
5. 0xa60199161a90d361f065927031891c9577c3b2581bd29fc622e40ce16463f5da
6. 0x2f4b07518e27a38f6b684cc559fb16690cea63081c3c1052e82679a39b077033
7. 0xeb12f0cb41136233b59f03c9e3597857937041ffd89396c6800dd87ce33bfd0a
8. 0x034f084c873bb629ef4ec19107c6240f7b11f423fa0599278ab5da84ee4e19e1
9. 0x1ebbc542318b231a68d9fff49411de41d04131ec1870317d564505ba96dcd348
10. 0x950742cf2cd20b757e056d776afc0e0e226d1d2ebfec405e3082bb34658b5e4a
11. 0x31293c2261c535896c5ddb291cbd32a12a457794940e30c3d3e1ded3b9c739ce
12. 0x9e12233d6ee4faeb9271b0fc3c834797517d702f44add023149f28a0809c0aaa
13. 0xe5a836cf25a8dfc72c9e3b6a69a7561a1f61f50f9cf36707d36f6e926aa15dec
14. 0xa96bb9408ce00a0d40ddaba8736257dfce76d5478b131d69db1afdf8a824312b
15. 0x7ddc2fead128357f881b63e6c7c26d7fbbb84fca6c7c8e0bbfe386de86ca8d39
16. 0xc6a4d7899a0f442958e26505011190b7cff2483611c1b94eba9043e0ba9ac36e
17. 0x8c756542e482157df0c36464d75c937b845e4423dbbcfad08f0cf8d5a16b9a13
18. 0x20704208aa6923d6b2450ef74ede87a6e0265d46447926038fe9506e9e154b2d
19. 0x9b9ce5b74b9bab5121612ef6b64920a8d453cbf311096a423eef9702747e868a

Day root

0xf43e8dcc3d451a4788b26be904c55e8c4c0fa75c9666796c51db38d37e2c0df8

Chained

0x702d5ac508f08b0d1accf36af25822d8e5660367494edd17a642fb61e158a57a

Published

On Arc Testnet, block 69251483: 0x495162f8936e19f0039918feebe6c307f327cd6bf8c37219620b1970041fa9ae