Evidence row 263379

What was observed

{
  "count": 14,
  "tools": [
    {
      "description": "Return the explainable trust score, label, scoring reasons, and verification history for an MCP server.",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "additionalProperties": false,
        "properties": {
          "slug": {
            "description": "Server slug",
            "type": "string"
          }
        },
        "required": [
          "slug"
        ],
        "type": "object"
      },
      "name": "check_trust"
    },
    {
      "description": "Compare two MCP servers side by side: trust, transport, tools, install, and links.",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "additionalProperties": false,
        "properties": {
          "a": {
            "description": "First server slug",
            "type": "string"
          },
          "b": {
            "description": "Second server slug",
            "type": "string"
          }
        },
        "required": [
          "a",
          "b"
        ],
        "type": "object"
      },
      "name": "compare_servers"
    },
    {
      "description": "Generate the install + client config for an MCP server in a given runtime (claude-desktop, cursor, vscode, windsurf, cline, continue, goose, openai-agents, langgraph, crewai).",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "additionalProperties": false,
        "properties": {
          "runtime": {
            "description": "Runtime slug, e.g. 'claude-desktop'",
            "type": "string"
          },
          "slug": {
            "description": "Server slug",
            "type": "string"
          }
        },
        "required": [
          "slug",
          "runtime"
        ],
        "type": "object"
      },
      "name": "generate_runtime_config"
    },
    {
      "description": "Find verified MCP servers with the same capabilities as a given server, ranked by trust.",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "additionalProperties": false,
        "properties": {
          "slug": {
            "description": "Server slug",
            "type": "string"
          }
        },
        "required": [
          "slug"
        ],
        "type": "object"
      },
      "name": "get_alternatives"
    },
    {
      "description": "List the best MCP servers that provide a capability (e.g. 'send-email', 'web-search'), ranked by trust.",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "additionalProperties": false,
        "properties": {
          "slug": {
            "description": "Capability slug, e.g. 'send-email'",
            "type": "string"
          }
        },
        "required": [
          "slug"
        ],
        "type": "object"
      },
      "name": "get_capability"
    },
    {
      "description": "Live snapshot of the indexed MCP ecosystem: totals (servers, tools, handshake-verified), provenance and transport breakdowns, and the current top-trust / most-adopted / newest / biggest-trust-riser servers.",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "properties": {},
        "type": "object"
      },
      "name": "get_ecosystem_stats"
    },
    {
      "description": "Fetch one curated loadout: its servers (each with role + LIVE trust/transport/tool-risk from the index), an aggregated governance posture for the whole kit, and the plays (see→decide→act sequences) it's designed to run.",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "additionalProperties": false,
        "properties": {
          "slug": {
            "description": "Loadout slug, e.g. 'gtm', 'coding', 'research'",
            "type": "string"
          }
        },
        "required": [
          "slug"
        ],
        "type": "object"
      },
      "name": "get_loadout"
    },
    {
      "description": "Fetch the full record for one MCP server by slug: install methods, tools, trust, verification, and provenance.",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "additionalProperties": false,
        "properties": {
          "slug": {
            "description": "Server slug, e.g. 'github'",
            "type": "string"
          }
        },
        "required": [
          "slug"
        ],
        "type": "object"
      },
      "name": "get_server"
    },
    {
      "description": "List the capability slugs an agent can filter or look up by (e.g. 'send-email', 'query-database'), most-populated first. Use these with get_capability or search_servers' capability filter — the taxonomy isn't guessable.",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "additionalProperties": false,
        "properties": {
          "limit": {
            "description": "Max capabilities (default 30)",
            "maximum": 100,
            "minimum": 1,
            "type": "integer"
          }
        },
        "type": "object"
      },
      "name": "list_capabilities"
    },
    {
      "description": "List curated loadouts — deliberately-assembled kits of MCP servers + governance + plays for a specific job (GTM, coding, research, support, infra). The agent-facing version of the /loadouts product. Use get_loadout for the full kit with live trust.",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "properties": {},
        "type": "object"
      },
      "name": "list_loadouts"
    },
    {
      "description": "List the runtimes generate_runtime_config supports (Claude Desktop, Cursor, VS Code, agent frameworks, …), with each one's config path. Enumerate these instead of guessing runtime slugs.",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "properties": {},
        "type": "object"
      },
      "name": "list_runtimes"
    },
    {
      "description": "Turn a plain-language goal into a recommended, governed toolset: the best-fit curated loadout (matched transparently by goal terms) plus an assembled set of the most relevant indexed servers, each with LIVE trust and tool-risk, and an aggregate governance posture for the kit. The decision layer over search/capability/trust/loadouts.",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "additionalProperties": false,
        "properties": {
          "goal": {
            "description": "What the agent should do, in plain language, e.g. 'triage support tickets and file bugs'.",
            "minLength": 3,
            "type": "string"
          },
          "limit": {
            "description": "Max assembled servers (default 6).",
            "maximum": 10,
            "minimum": 1,
            "type": "integer"
          },
          "risk_tolerance": {
            "description": "'read-only' restricts the assembled set to servers with no write/destructive tools — the safe set for an unsupervised agent. Default 'any'.",
            "enum": [
              "any",
              "read-only"
            ],
            "type": "string"
          }
        },
        "required": [
          "goal"
        ],
        "type": "object"
      },
      "name": "plan_toolset"
    },
    {
      "description": "Report that an MCP server's install, docs, or endpoint is broken. Creates a submission for editorial review.",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "additionalProperties": false,
        "properties": {
          "detail": {
            "description": "What's broken (install fails, endpoint down, docs wrong, …)",
            "maxLength": 1000,
            "type": "string"
          },
          "slug": {
            "description": "Server slug",
            "type": "string"
          }
        },
        "required": [
          "slug",
          "detail"
        ],
        "type": "object"
      },
      "name": "report_broken_server"
    },
    {
      "description": "Search the MCPExplorer index of MCP servers by free text and filters. Omit `query` to browse the whole index ranked by trust score. Every filter either applies or is echoed back in `ignored_filters` with a reason — filters never silently do nothing.",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "additionalProperties": false,
        "properties": {
          "capability": {
            "description": "Filter to servers providing a capability slug, e.g. 'send-email'. An unknown slug is reported in ignored_filters, not silently dropped.",
            "type": "string"
          },
          "limit": {
            "description": "Max results (default 10)",
            "maximum": 50,
            "minimum": 1,
            "type": "integer"
          },
          "official_status": {
            "description": "Filter by provenance",
            "enum": [
              "official",
              "partner",
              "community",
              "unknown"
            ],
            "type": "string"
          },
          "query": {
            "description": "Free-text query, e.g. 'send email' or 'postgres'. Omit to browse the full index ranked by trust.",
            "type": "string"
          },
          "risk_level": {
            "description": "Filter by tool risk. 'read-only' = has tools and none are write/destructive — the safe set to hand an autonomous agent.",
            "enum": [
              "read-only",
              "read",
              "write",
              "destructive"
            ],
            "type": "string"
          },
          "transport": {
            "description": "Filter by transport. Many servers are still 'unknown' (transport not yet probed by the crawler).",
            "enum": [
              "stdio",
              "sse",
              "streamable_http",
              "websocket",
              "unknown"
            ],
            "type": "string"
          }
        },
        "type": "object"
      },
      "name": "search_servers"
    }
  ]
}

What the leaf hashes

{"body":"1e9300426ff0eec30509d1d68a5e1a1e6cf2ec0d32949ea45def579c3c8d2602","id":263379,"kind":"mcp.tools","method":"probe.mcp/1","observed_us":1793033408629522,"prev":null,"subject":"26123cc7-712a-4b17-ac15-d117c66b412e","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. 0xc2edd018250ef2e993a10d5d253339d82069baed9ef9d5ea94b05a25fc2b3f7f
2. 0xa91d031a78d729c962cc525645fa1518b39ed8a486bfcd013b4933db479bdbf8
3. 0x388f801b1e25b48dbd93074919cdaa93f6275b83cd0110d77f0734131bd12ddf
4. 0x208c8a67fef8e8add7b43bea3ef538474af29bbcca7298d60ef9e7c6123881b5
5. 0xc880ee4e2971dc858d8619b0871e82ef6de2023775c91be91e093ee6b6df1936
6. 0x12268a555d266516c8f097f111489ed9244070f2c72669e9f69c05ac8238bb37
7. 0xb197fba1011a120b5ce807fb385dc9958aa427334b19c63d3ed0b3919d4c6a7f
8. 0x9b72fefe591a2700c562fb84983443d0093c455196167af39b4b3d5b92106300
9. 0x2eaec7be5e939f8e37b9ab727fbcfdd2cade093a31bba6c674df4f6089f70666
10. 0x00d960df50a5325e5736603a5a0d0a56310dedcefbef5371376f8262982d78ed
11. 0x7f4ae229fdca48d3ef8476aa02e4d171abb9d529ffe12fe147f9a22b16589b6a
12. 0x63002f2569d43725bbf2d04d90ec9e6cf925c96b6dda5e7e220ecfbdd9c2444d
13. 0x641fba1f23ec69d96721e34ace1926954d835b9614cb5eae215a069c056399b8
14. 0xdbe2e8dd65ea1248b2936612538f18268abd5cf27ebdab3737694571ad496004
15. 0x9f68b5e15459cb62b8c0cd4c124fa61c74147b4a5755a200fbecd21a581635d1
16. 0x123ec8bee20ddc55223eeef5a4f4d6c4b6416515adbb911c56759f5cde56e452
17. 0xd0651cb9bc8155eb52b5247d506e74b8a935057dc190ba52091702ac25ed3a40
18. 0x9a9024edb5069d88a324facb310a5ce8e495214bbaa968f077bede437390194f
19. 0x9b9ce5b74b9bab5121612ef6b64920a8d453cbf311096a423eef9702747e868a

Day root

0xf43e8dcc3d451a4788b26be904c55e8c4c0fa75c9666796c51db38d37e2c0df8

Chained

0x702d5ac508f08b0d1accf36af25822d8e5660367494edd17a642fb61e158a57a

Published

On Arc Testnet, block 69251483: 0x495162f8936e19f0039918feebe6c307f327cd6bf8c37219620b1970041fa9ae