Evidence row 1243182

What was observed

{
  "count": 14,
  "tools": [
    {
      "description": "Use this when you need to add VAT to a net amount or take it out of a gross amount. Example prompt: \"What is 21% BTW on 1,250 euros?\" Add VAT to a net amount or extract VAT from a gross amount at any rate (e.g. 21 for Dutch BTW). Returns exact net, VAT, and gross amounts rounded to cents. Costs 1 credit. The answer is deterministic.",
      "inputSchema": {
        "properties": {
          "amount": {
            "description": "The amount",
            "minimum": 0,
            "type": "number"
          },
          "mode": {
            "description": "add = amount is net, add VAT on top; extract = amount is gross, split out VAT",
            "enum": [
              "add",
              "extract"
            ],
            "type": "string"
          },
          "rate": {
            "description": "VAT rate in percent",
            "maximum": 100,
            "minimum": 0,
            "type": "number"
          }
        },
        "required": [
          "amount",
          "rate",
          "mode"
        ],
        "type": "object"
      },
      "name": "calculate_vat"
    },
    {
      "description": "Use this when you need CSV data as JSON objects. Example prompt: \"Turn this CSV export into JSON.\" Parse CSV data into JSON with delimiter auto-detection and quoted-field handling. Costs 1 credit. The answer is deterministic.",
      "inputSchema": {
        "properties": {
          "csv": {
            "description": "The CSV text; the delimiter is detected automatically",
            "maxLength": 200000,
            "type": "string"
          },
          "firstRowHeaders": {
            "default": true,
            "description": "Treat the first row as column names and return objects (default true)",
            "type": "boolean"
          }
        },
        "required": [
          "csv"
        ],
        "type": "object"
      },
      "name": "csv_to_json"
    },
    {
      "description": "The full definition of one ToolForte tool by name: description, argument schema (JSON Schema), output schema, annotations, cost and an example call. Use it after search_tools when the argument summary is not enough. Free.",
      "inputSchema": {
        "properties": {
          "name": {
            "description": "The tool name, for example validate_iban",
            "maxLength": 80,
            "type": "string"
          }
        },
        "required": [
          "name"
        ],
        "type": "object"
      },
      "name": "describe_tool"
    },
    {
      "description": "Use this when you need the dates of the Dutch public holidays in a given year. Example prompt: \"When is Ascension Day in the Netherlands in 2027?\" Exact Dutch public holidays for a year, including movable feasts (Easter, Ascension, Whitsun) and King's Day rules. Use this instead of computing Dutch holidays yourself. Costs 1 credit. The answer is deterministic.",
      "inputSchema": {
        "properties": {
          "year": {
            "description": "Calendar year, 1900 to 2200",
            "maximum": 2200,
            "minimum": 1900,
            "type": "integer"
          }
        },
        "required": [
          "year"
        ],
        "type": "object"
      },
      "name": "dutch_public_holidays"
    },
    {
      "description": "Use this when you need to check whether JSON is valid or make it readable. Example prompt: \"Why does this JSON fail to parse?\" Validate and pretty-print JSON with a real parser. Returns formatted JSON or the exact parse error. Costs 1 credit. The answer is deterministic.",
      "inputSchema": {
        "properties": {
          "indent": {
            "default": 2,
            "description": "Spaces per indentation level, 0 to 8 (default 2)",
            "maximum": 8,
            "minimum": 0,
            "type": "integer"
          },
          "json": {
            "description": "The JSON text to validate and format",
            "maxLength": 200000,
            "type": "string"
          }
        },
        "required": [
          "json"
        ],
        "type": "object"
      },
      "name": "format_json"
    },
    {
      "description": "Run any ToolForte tool by name with its arguments, whether or not it is listed in this session. The result, the cost and the metering are exactly what the tool gives when called directly; run_tool itself is free. Find names with search_tools and schemas with describe_tool.",
      "inputSchema": {
        "properties": {
          "arguments": {
            "additionalProperties": {},
            "default": {},
            "description": "The tool's arguments, as describe_tool documents them",
            "propertyNames": {
              "type": "string"
            },
            "type": "object"
          },
          "name": {
            "description": "The tool name, for example calculate_vat",
            "maxLength": 80,
            "type": "string"
          }
        },
        "required": [
          "name"
        ],
        "type": "object"
      },
      "name": "run_tool"
    },
    {
      "description": "Use this when you need a ToolForte tool that is not in the current tool list. Example prompt: \"Is there a tool that converts YAML to JSON?\" Find ToolForte tools by what you want done, for example \"iban\", \"vat\", \"pdf merge\", \"working days\", \"csv to json\", \"screenshot\". ToolForte has over a hundred exact tools (validation, conversion, Dutch tax and dates, test data, files, AI); a session lists a small core of them and this is how you reach the rest. Returns the best matches with their arguments and cost. Then call the tool by name, or through run_tool. Free. The answer is deterministic.",
      "inputSchema": {
        "properties": {
          "limit": {
            "default": 8,
            "description": "How many matches to return, 1 to 50 (default 8)",
            "maximum": 50,
            "minimum": 1,
            "type": "integer"
          },
          "query": {
            "default": "",
            "description": "Words describing the job. Empty lists every tool the server has.",
            "maxLength": 200,
            "type": "string"
          }
        },
        "type": "object"
      },
      "name": "search_tools"
    },
    {
      "description": "Use this when you need to know what a regular expression actually matches. Example prompt: \"Does this regex match every email address in this text?\" Run a JavaScript regular expression against a test string using a real regex engine. Returns all matches with capture groups and indices. Costs 1 credit. The answer is deterministic.",
      "inputSchema": {
        "properties": {
          "flags": {
            "default": "g",
            "description": "Regex flags such as g, i, m, s, u (default g)",
            "maxLength": 8,
            "type": "string"
          },
          "pattern": {
            "description": "JavaScript regular expression source, without the slashes",
            "maxLength": 1000,
            "type": "string"
          },
          "text": {
            "description": "The text to run the expression against",
            "maxLength": 20000,
            "type": "string"
          }
        },
        "required": [
          "pattern",
          "text"
        ],
        "type": "object"
      },
      "name": "test_regex"
    },
    {
      "description": "Use this when you need to see exactly which lines changed between two versions of a text. Example prompt: \"What changed between these two versions of the contract clause?\" Compute an exact line-based diff between two texts with add/remove/unchanged stats. Costs 1 credit. The answer is deterministic.",
      "inputSchema": {
        "properties": {
          "modified": {
            "description": "The text after the change",
            "maxLength": 100000,
            "type": "string"
          },
          "original": {
            "description": "The text before the change",
            "maxLength": 100000,
            "type": "string"
          }
        },
        "required": [
          "original",
          "modified"
        ],
        "type": "object"
      },
      "name": "text_diff"
    },
    {
      "description": "Use this when you need to know whether an IBAN is well formed before using it. Example prompt: \"Is NL91ABNA0417164300 a valid IBAN?\" Check whether an IBAN is well formed: the mod-97 checksum, the country code, the length that country's IBAN must have, and whether every position holds the kind of character that country allows there (mod-97 turns letters into numbers, so on its own it cannot see a capital O typed in place of a zero). Returns validity, country, and where known the bank identifier printed inside the IBAN. This is a format check, not a bank check: a passing IBAN can still name a bank code that never existed or has since merged away, and says nothing about whether the account exists or can receive a payment. For twelve countries it also verifies the national check digit that the bank computes over the bank code and account number (BE, FR, MC, ES, IT, SM, PT, SI, PL, TN, EE, HU); nationalCheck 'failed' there means the number is very probably invented, since that digit cannot be back-computed the way the mod-97 pair can. Absent nationalCheck means not checked, never approved. For Dutch IBANs it also names the institution behind the four-letter bank code, including codes that no longer issue accounts; an unrecognised code does not make the IBAN invalid. A territory that borrows another country's IBAN (Reunion, Guernsey, Aland and the like) is reported with the prefix it actually uses, since no IBAN starts with RE or GG. Never guess whether an IBAN is well formed: use this tool. Do not present a pass as confirmation that money can be sent. Costs 1 credit. The answer is deterministic.",
      "inputSchema": {
        "properties": {
          "iban": {
            "description": "The IBAN to validate",
            "maxLength": 64,
            "type": "string"
          }
        },
        "required": [
          "iban"
        ],
        "type": "object"
      },
      "name": "validate_iban"
    },
    {
      "description": "List the workflows saved to the ToolForte account this API key belongs to. A workflow runs several ToolForte tools in order, passing each one the output of an earlier step, so it does a whole job in one call instead of you orchestrating the steps yourself. Returns each workflow's id, the inputs it expects, the steps it runs and what a run costs. Call this first: workflow_run needs an id from here. Requires an API key, because a workflow belongs to an account. Get a key in one request with POST https://toolforte.com/api/v1/keys/bootstrap and {\"email\":\"you@example.com\"}, which emails it to that address, or create one at https://toolforte.com/developers, and send it on the MCP connection as the header Authorization: Bearer tf_...",
      "inputSchema": {
        "properties": {
          "limit": {
            "default": 50,
            "description": "How many to return, newest first.",
            "maximum": 200,
            "minimum": 1,
            "type": "integer"
          }
        },
        "type": "object"
      },
      "name": "workflow_list"
    },
    {
      "description": "Describe a job in plain words and get back a workflow built only from tools this server really has: a name, the inputs it needs, and the steps in order, each with one sentence on why it is there. The proposal is honest about gaps: partial is true and missing names what could not be done, and when nothing here fits the answer says so instead of inventing a step. Send save: true to keep it on the account, after which workflow_run can run it by the returned id. Costs 10 credits, the price of one AI generation, charged once per proposal. Requires an API key linked to a ToolForte account. Get a key in one request with POST https://toolforte.com/api/v1/keys/bootstrap and {\"email\":\"you@example.com\"}, which emails it to that address, or create one at https://toolforte.com/developers, and send it on the MCP connection as the header Authorization: Bearer tf_...",
      "inputSchema": {
        "properties": {
          "goal": {
            "description": "The job to be done, in a sentence or two, for example: take a CSV of invoices, sum the amounts per customer and write the totals to a spreadsheet.",
            "maxLength": 1000,
            "minLength": 8,
            "type": "string"
          },
          "save": {
            "default": false,
            "description": "Save the proposed workflow to the account so workflow_run can run it. Default false: the proposal is returned for you to read first.",
            "type": "boolean"
          }
        },
        "required": [
          "goal"
        ],
        "type": "object"
      },
      "name": "workflow_propose"
    },
    {
      "description": "Run one saved workflow by id and return what every step produced. Get the id and the input keys from workflow_list. Each step costs the credits its own tool costs, normally 1 per step, and the credit for this call counts as the first step's rather than being charged on top. Steps run in order and stop at the first failure; the result says which step stopped it and what was spent up to that point. Check the \"substitutions\" field when it is present: it lists values a step supplied that the tool replaced with its own, which means the run succeeded on a value you did not send. Requires an API key, because a workflow belongs to an account. Get a key in one request with POST https://toolforte.com/api/v1/keys/bootstrap and {\"email\":\"you@example.com\"}, which emails it to that address, or create one at https://toolforte.com/developers, and send it on the MCP connection as the header Authorization: Bearer tf_...",
      "inputSchema": {
        "properties": {
          "inputs": {
            "additionalProperties": {},
            "description": "Values for the workflow's declared inputs, keyed by the input key that workflow_list reports. Omit for a workflow that declares none.",
            "propertyNames": {
              "type": "string"
            },
            "type": "object"
          },
          "workflowId": {
            "description": "The id of a workflow from workflow_list.",
            "maxLength": 100,
            "type": "string"
          }
        },
        "required": [
          "workflowId"
        ],
        "type": "object"
      },
      "name": "workflow_run"
    },
    {
      "description": "Use this when you need the number of working days between two dates. Example prompt: \"How many working days are there between 1 March and 30 April 2027?\" Count working days (Mon-Fri) between two dates inclusive, optionally excluding Dutch public holidays. Exact date math for SLA, payroll, and planning questions. Costs 1 credit. The answer is deterministic.",
      "inputSchema": {
        "properties": {
          "end": {
            "description": "YYYY-MM-DD",
            "pattern": "^\\d{4}-\\d{2}-\\d{2}$",
            "type": "string"
          },
          "excludeDutchHolidays": {
            "default": true,
            "description": "Skip Dutch public holidays that fall on a weekday (default true)",
            "type": "boolean"
          },
          "start": {
            "description": "YYYY-MM-DD",
            "pattern": "^\\d{4}-\\d{2}-\\d{2}$",
            "type": "string"
          }
        },
        "required": [
          "start",
          "end"
        ],
        "type": "object"
      },
      "name": "working_days_between"
    }
  ]
}

What the leaf hashes

{"body":"2ab61366359c1dfed55eeaeb4204afa6ecd8d9156ca98bd47e671e565beee450","id":1243182,"kind":"mcp.tools","method":"probe.mcp/1","observed_us":1793358949939777,"prev":null,"subject":"1fd5ae9e-f65a-4433-ad27-477cefb3ed5c","subject_kind":"endpoint"}

Proof

Fold these into the leaf in order, hashing each sorted pair with keccak256, to reach the root of 2026-10-30 (243099 rows).

1. 0xe523709e4464bba786992608c0ad27b5ce96468c55cbf9b66104914402bf2c7a
2. 0xf7241b968547e84f5fd1c9d82a93a2e2451283a0c22e755604637cf8ca054713
3. 0x717fcb0552ff1769549bddfe12d0be1c1cfd69c9ad746268a3ac2225fd75b53a
4. 0xc46d2975363206373900be52c538f986e49fd4fcc04c7e8e2689d3060dee72f7
5. 0x8e905e48f6d77052cd05e5c8cc689447fb4c68d936b5d8bdf14396e644c9693c
6. 0x9a68e939c1c60a4fabd3bccc8e320d97d52e9e44f8a7cf5ebb5a51b913071a9e
7. 0xe19d8b06717f6ff3c691dd109784f4cbcbc387dda8c16c3997516359d050444a
8. 0x14dd11a164d4eeb149b5a5939331b06935ab5c955632289488406d29cee2598c
9. 0xae3f9145f8b2378b265d40f9ff0d2b8bdad71127a0c26f512947450a89f332bf
10. 0x8a10fb0a3c74c7daf69e6680dc961b6d5477c1971040e10bc6fd58d7df2d885c
11. 0x87432c8539926003bf4ca7e853841aca0a44163565bdd5782c85888ccb003210
12. 0x0221926da48f1be0858f9f5f2ad1881d381008bbf8c70e9c06bb1a63fd6faa7e
13. 0xfbc54bb68398dda4b439809764b90c546b18332d8f5c47b62a26f520efc65735
14. 0x3a7a0fa82cbf8d3f1546fc6f89c9a5f35e025db7170b70e3f2dcd72b4ebb0f8e
15. 0xea7df1002501052c124b5aed2b1a5df3d59be54394c6a8539c86fad1df339a9e
16. 0xfbe61dc2d59668ac573e5eab865747e21d38bf2fe4c64762beef01f1018a4dea
17. 0x71e74c274b23c9047354edb6dcd2c654415e3986b8bd875dae992996ea12e22b
18. 0x0c43c73b62a5d49ee1444b5dc4195fc5b16b141d3f4458e2e9fbd5fd6ecb367d

Day root

0x0826c7ad6039e06a2360ca0a4a3a4fe7f2626c6dc19f71a37599386f78b39875

Chained

0x36b4c8a1063758f0b8765fa1bdf75fa92fb543cc183add3e261880ee2bd1f822

Published

On Arc Testnet, block 69923247: 0x8704744146c6967c8abc9e9a99de4db7283b29e840922ea83a69b6fe776e6861