Evidence row 2566767

What was observed

{
  "count": 6,
  "tools": [
    {
      "description": "Check a stack of two to ten tools against every CDP in CdpHub's directory, as the stack check on cdphub.com does: how many CDPs list all of them and which, those CDPs grouped by how they connect to each tool with each group counted, how they connect to each tool on its own with each group counted and a sentence for it, the CDPs that miss exactly one tool grouped by the tool they miss, and a link to the same check on cdphub.com. Use it for any question about two or more tools together, such as which CDPs fit a company's stack.",
      "inputSchema": {
        "additionalProperties": false,
        "properties": {
          "tools": {
            "description": "The tools, for example [\"Shopify\", \"Klaviyo\", \"Snowflake\"]: two to ten.",
            "items": {
              "type": "string"
            },
            "maxItems": 10,
            "minItems": 2,
            "type": "array"
          }
        },
        "required": [
          "tools"
        ],
        "type": "object"
      },
      "name": "check_stack"
    },
    {
      "description": "Compare two CDPs' integration catalogs in CdpHub's directory, tool by tool: how many tools both list, how many only one does, the most widely listed tools in both, each side's largest categories of tools the other lacks, and the link to their comparison page on cdphub.com.",
      "inputSchema": {
        "additionalProperties": false,
        "properties": {
          "a": {
            "description": "The first CDP, for example \"Segment\".",
            "type": "string"
          },
          "b": {
            "description": "The second CDP, for example \"mParticle\".",
            "type": "string"
          }
        },
        "required": [
          "a",
          "b"
        ],
        "type": "object"
      },
      "name": "compare_cdps"
    },
    {
      "description": "Look up one customer data platform's integration catalog in CdpHub's directory: its number of tools and listings and its rank by catalog size, which way its integrations run, its largest categories with their most widely listed tools, how it connects to the main data warehouses, the CDPs that list the most of the same tools, and its page on cdphub.com.",
      "inputSchema": {
        "additionalProperties": false,
        "properties": {
          "name": {
            "description": "The CDP, for example \"Segment\", \"Braze\" or \"Adobe Experience Platform\".",
            "type": "string"
          }
        },
        "required": [
          "name"
        ],
        "type": "object"
      },
      "name": "get_cdp"
    },
    {
      "description": "Look up one marketing or data tool (for example Snowflake, Braze, Google Ads or The Trade Desk) in CdpHub's directory: how many of the customer data platforms (CDPs) it tracks list an integration with it, each CDP counted once (both sends data to it and reads from it, only sends, only reads), which CDPs list it in each group and which don't, every listing with its direction, how it runs (server-side, client-side, in the warehouse) and a link to the CDP's own documentation, and the tool's page on cdphub.com. Use it for any question about one tool.",
      "inputSchema": {
        "additionalProperties": false,
        "properties": {
          "name": {
            "description": "The tool, for example \"Snowflake\" or \"Google Ads\".",
            "type": "string"
          }
        },
        "required": [
          "name"
        ],
        "type": "object"
      },
      "name": "get_tool"
    },
    {
      "description": "List every customer data platform in CdpHub's directory with its number of tools and listings and its page on cdphub.com, largest catalog first, with the directory's totals.",
      "inputSchema": {
        "additionalProperties": false,
        "properties": {},
        "type": "object"
      },
      "name": "list_cdps"
    },
    {
      "description": "Search CdpHub's directory of CDP integrations by keyword, CDP, category, direction or how the integration runs. Returns the exact totals, the first results and the link to the same search on cdphub.com. Use get_tool for one named tool and check_stack for several.",
      "inputSchema": {
        "additionalProperties": false,
        "properties": {
          "categories": {
            "description": "Only these categories, for example [\"Advertising\"].",
            "items": {
              "type": "string"
            },
            "type": "array"
          },
          "cdps": {
            "description": "Only these CDPs, for example [\"Tealium\"].",
            "items": {
              "type": "string"
            },
            "type": "array"
          },
          "directions": {
            "description": "Which way data moves, from the CDP's side: \"out\" sends data to the tool, \"into\" reads from it, \"both\", or \"unknown\" when the listing doesn't say.",
            "items": {
              "enum": [
                "out",
                "into",
                "both",
                "unknown"
              ],
              "type": "string"
            },
            "type": "array"
          },
          "group": {
            "description": "Group the results by tool or by listing. Leave it out to let the directory decide.",
            "enum": [
              "tool",
              "listing"
            ],
            "type": "string"
          },
          "query": {
            "description": "Words to search for in tool, listing and CDP names, categories and descriptions, for example \"reverse etl\".",
            "type": "string"
          },
          "runs": {
            "description": "How the integration runs: server-side, client-side, through a warehouse, or \"none\" when the listing doesn't say.",
            "items": {
              "enum": [
                "server",
                "client",
                "warehouse",
                "none"
              ],
              "type": "string"
            },
            "type": "array"
          },
          "sort": {
            "description": "The result order. Leave it out to let the directory decide.",
            "enum": [
              "relevance",
              "coverage",
              "az",
              "added",
              "recommended"
            ],
            "type": "string"
          }
        },
        "type": "object"
      },
      "name": "search_directory"
    }
  ]
}

What the leaf hashes

{"body":"51886cb76c81161537d2d729d46af98e8afe8280ff8236d910b491fe04fa28cc","id":2566767,"kind":"mcp.tools","method":"probe.mcp/1","observed_us":1793702273956495,"prev":1257925,"subject":"b59cea28-1b93-4cf5-8ab6-f777c98c6289","subject_kind":"endpoint"}

Proof

Fold these into the leaf in order, hashing each sorted pair with keccak256, to reach the root of 2026-11-03 (425475 rows).

1. 0xc55ded8c3046f4b8e850d4b0b04bac35ee0b2e600e8c1855e07182647869ab03
2. 0xac6ef2a45572b955dab04abcda9f5e4aed4d4efa12970ac89f8aae05bcf2c857
3. 0xa2f834e98aa404bf2c1d334ecba3d8318166755666784c65cd2ca1f3e41a9a7b
4. 0x6f6afe68c08c5287e8fd726c4ccfa9bdb312bb31a3ca6a66dbb1257031dc642f
5. 0x5949ca6b92f4844e4238dd6504225883151fffcafb82749e3ab79ca1aba87602
6. 0x7f9e0cb30d39290c572a46969cf9c42e601dc60d7583221529c689d8e10711d1
7. 0x0c25c8cf57c5edfdbc8141e833d6439287a5cb4068762e031f927fb53b56cd37
8. 0xee452bf7a7b08cb99fb92d46502a6a5da175e5add6dbe05cab9abc3cf01bed62
9. 0x66671ef5cf74da00e2ebbd8ee9ac6de6decec70cbdf5e41cd9c3792855c0ee00
10. 0x542e3668c1549d9a8de999162a765a8d095b38037d7364287ce5870862eacaf1
11. 0xb9479538c0cf9567cbeefd29a4239e2a9b423f88542d2090e7f65ae17fe08d95
12. 0x2776d6de184337d929278006b07b17c87f04f4b0c2a6ef891d856846b26b3417
13. 0x757c81f4c079ccef5ee9694c28de1354dd783331e9778583284b2bcba45c4662
14. 0xad3757a4386398bde7b5dfd7d1ed0d8391a8487b9cbded422b75d61d77ec3baf
15. 0x20b1beb78a0f066bfa1ffbab05695dfb2940fd2df005cdcab3ae2e82d26c01a9
16. 0x59b3a6fae1c920f45b1445649e93c8c7d68f3f69789b0df88522cdb15a28590b
17. 0x7075a090980aecb33e9c15c829cb40f5b44385b6d91a159042263db068126b87
18. 0xac5402954216dc6c7020a6405675c8fc3b0828c2ab02943d80de52677a2f1fc3
19. 0x85f3a27c16056a361d9ba33355a575ca7123f86de901b204c88953c4b8ea441a

Day root

0xb646ffa569e24bf8336b0a15a9d98d0a2f1239f58e10c2b18a9d22e43343566a

Chained

0x35e926359fd19031c6b5e08fb3b44f2524386a57c8fdd353336c185603f53d43

Published

On Arc Testnet, block 70601990: 0xa5f9dadba13cde129126b950e64b815e6833cb8ff53b75026c9dbe769c3768c7