← The evidence ledger
Evidence row 221924
Observed , by probe.mcp/1.
- Kind
- mcp.tools
- About
- endpoint a3fc06d8-2cc8-4508-acdd-0f4cc754e92a
- Recorded
- Previous row
- None: the first of its kind about this subject
- Body SHA-256
- 3b18906c5ee2e64b245073eb5c06cbc531e578125b895937af042900ff175dc2
- Leaf
- 0x1768b993c71d0a0d1cd65cabf372892c955031999d80f930751c5376e6ae9dc6
What was observed
{
"count": 6,
"tools": [
{
"description": "Compare Grandet model prices within each unit. Read listings for price-only ordering and conditions; legacy recommended/alternative/cheapest retain their old meanings. Use view=compact for shared connection cards and a short text response. Provide exactly one model or name selector. host records the source only and never selects the inference route. Send targetApp when the user or conversation identifies the intended API application, including explicit use in the current app. With no target, compare directly. An unrecorded app connection permits a price-only recommendation, not a compatibility claim. Omit profile/protocol for a multi-protocol app unless already specified. Existing client remains a legacy target-app alias. Infer coding/chat/long_output from the task; presets are estimates. Use grandet_list_apps only when application facts are needed. Do not request API keys.",
"inputSchema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"additionalProperties": false,
"properties": {
"asOf": {
"description": "Evaluate as of this UTC time (ISO 8601, e.g. \"2026-10-16T12:00:00Z\"). Omit to evaluate now.",
"maxLength": 256,
"minLength": 1,
"type": "string"
},
"channel": {
"description": "\"standard\" (default) lists ordinary channels, \"declared-nonstandard\" only channels the site itself labels nonstandard, \"all\" both.",
"enum": [
"standard",
"declared-nonstandard",
"all"
],
"type": "string"
},
"client": {
"description": "Legacy alias of targetApp. Prefer targetApp.",
"pattern": "^[a-zA-Z0-9._/-]{1,64}$",
"type": "string"
},
"currency": {
"description": "Limit to one unit board: USD_CREDIT or CNY_CREDIT (site credit, not cash), USD or CNY (cash). Never compare prices across units.",
"enum": [
"USD_CREDIT",
"CNY_CREDIT",
"USD",
"CNY"
],
"type": "string"
},
"endpointType": {
"description": "Limit to one API protocol. Send it only when the user named a protocol.",
"enum": [
"openai",
"openai-response",
"anthropic",
"gemini"
],
"type": "string"
},
"host": {
"description": "The assistant or app making this call, e.g. \"claude-code\" or \"codex\". Attribution only; it does not change results.",
"pattern": "^[a-zA-Z0-9._/-]{1,64}$",
"type": "string"
},
"lang": {
"default": "en",
"description": "Answer language: \"en\" or \"zh-CN\".",
"enum": [
"en",
"zh-CN"
],
"type": "string"
},
"limit": {
"default": 5,
"description": "Rows per block, 1–20 (default 5).",
"maximum": 20,
"minimum": 1,
"type": "integer"
},
"mix": {
"description": "Workload used to blend input, cache and output prices into one price per million total tokens. Presets \"chat\" (default), \"coding\" and \"long_output\", or custom input/cache-read/output/cache-write shares totalling 100.",
"maxLength": 120,
"type": "string"
},
"model": {
"description": "Model to look up: a catalogue ID, an exact model name or a natural name such as \"claude-sonnet-5-5\". Send exactly one of model or name. An ambiguous name returns NEEDS_CLARIFICATION with candidates.",
"maxLength": 256,
"minLength": 1,
"type": "string"
},
"name": {
"description": "The catalogue's 20-character hexadecimal raw-name ID (not the name text). Send exactly one of model or name.",
"maxLength": 256,
"minLength": 1,
"type": "string"
},
"os": {
"default": "unknown",
"description": "Operating system the target app runs on, for connection steps: windows, macos, linux or unknown.",
"enum": [
"windows",
"macos",
"linux",
"unknown"
],
"type": "string"
},
"plans": {
"description": "\"best\" (default) keeps one group per site; \"all\" lists every group of every site.",
"enum": [
"best",
"all"
],
"type": "string"
},
"releaseSet": {
"description": "Pin a published data release by its release-set hash. Omit to use the current release.",
"maxLength": 256,
"minLength": 1,
"type": "string"
},
"skillBuild": {
"description": "Grandet Skill build ID when called from the Skill. Omit otherwise.",
"maxLength": 256,
"type": "string"
},
"skillVersion": {
"description": "Grandet Skill version when called from the Skill, e.g. \"0.3.0\". Omit otherwise.",
"maxLength": 32,
"type": "string"
},
"targetApp": {
"description": "Catalogue ID of the app that will use the API, e.g. \"openclaw\", \"claude-code\" or \"codex\". Selects compatible protocols and connection steps. Send it only when the user says where the API will be used.",
"pattern": "^[a-zA-Z0-9._/-]{1,64}$",
"type": "string"
},
"targetProfile": {
"description": "An inference profile ID of the target app (see grandet_list_apps). Only together with targetApp or client.",
"pattern": "^[a-zA-Z0-9._/-]{1,64}$",
"type": "string"
},
"view": {
"default": "compact",
"description": "\"compact\" (default): a short text summary plus the listings, with connection cards shared in integrationCards; about a third of the size. \"full\": every legacy field, with the whole JSON repeated as text.",
"enum": [
"full",
"compact",
"brief"
],
"type": "string"
}
},
"type": "object"
},
"name": "grandet_find_cheapest_api"
},
{
"description": "Find current official free tiers, application-based credits and relay free groups. Return the stated benefit, six requirements, deadline, original observation and claim link. userCanMeet=no_card excludes explicit required/conditional card entries; unknown card requirements remain clearly labelled unknown. Application categories describe programs, not the user’s eligibility. Follow pagination.",
"inputSchema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"additionalProperties": false,
"properties": {
"asOf": {
"description": "Evaluate as of this UTC time (ISO 8601, e.g. \"2026-10-16T12:00:00Z\"). Omit to evaluate now.",
"maxLength": 256,
"minLength": 1,
"type": "string"
},
"host": {
"description": "The assistant or app making this call, e.g. \"claude-code\" or \"codex\". Attribution only; it does not change results.",
"pattern": "^[a-zA-Z0-9._/-]{1,64}$",
"type": "string"
},
"kind": {
"description": "\"official\" free tiers and credits, \"relay\" free groups, or \"all\".",
"enum": [
"official",
"relay",
"all"
],
"type": "string"
},
"lang": {
"default": "en",
"description": "Answer language: \"en\" or \"zh-CN\".",
"enum": [
"en",
"zh-CN"
],
"type": "string"
},
"limit": {
"description": "Results per page, 1–20.",
"maximum": 20,
"minimum": 1,
"type": "integer"
},
"page": {
"description": "Result page, starting at 1.",
"maximum": 99999,
"minimum": 1,
"type": "integer"
},
"q": {
"description": "Model, vendor or site to search, e.g. \"gemini\".",
"maxLength": 200,
"type": "string"
},
"releaseSet": {
"description": "Pin a published data release by its release-set hash. Omit to use the current release.",
"maxLength": 256,
"minLength": 1,
"type": "string"
},
"skillBuild": {
"description": "Grandet Skill build ID when called from the Skill. Omit otherwise.",
"maxLength": 256,
"type": "string"
},
"skillVersion": {
"description": "Grandet Skill version when called from the Skill, e.g. \"0.3.0\". Omit otherwise.",
"maxLength": 32,
"type": "string"
},
"targetApp": {
"description": "Catalogue ID of the app that will use the API, e.g. \"openclaw\", \"claude-code\" or \"codex\". Selects compatible protocols and connection steps. Send it only when the user says where the API will be used.",
"pattern": "^[a-zA-Z0-9._/-]{1,64}$",
"type": "string"
},
"userCanMeet": {
"description": "Only offers the user can meet: \"any\", \"no_card\" (no payment card) or \"student\".",
"enum": [
"any",
"no_card",
"student"
],
"type": "string"
},
"view": {
"default": "compact",
"description": "\"compact\" (default): about 18 KB for a typical query. \"full\": every field, often over 250 KB.",
"enum": [
"full",
"compact"
],
"type": "string"
}
},
"type": "object"
},
"name": "grandet_find_free_credits"
},
{
"description": "Look up the published Grandet relay glossary. Site labels are source claims and glossary terms explain them; they do not verify quality. Query q or category and follow pagination. Unknown terms include up to three related FAQ links.",
"inputSchema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"additionalProperties": false,
"properties": {
"category": {
"description": "Limit to one glossary category.",
"maxLength": 64,
"type": "string"
},
"host": {
"description": "The assistant or app making this call, e.g. \"claude-code\" or \"codex\". Attribution only; it does not change results.",
"pattern": "^[a-zA-Z0-9._/-]{1,64}$",
"type": "string"
},
"lang": {
"default": "en",
"description": "Answer language: \"en\" or \"zh-CN\".",
"enum": [
"en",
"zh-CN"
],
"type": "string"
},
"limit": {
"description": "Results per page, 1–20.",
"maximum": 20,
"minimum": 1,
"type": "integer"
},
"page": {
"description": "Result page, starting at 1.",
"minimum": 1,
"type": "integer"
},
"q": {
"description": "Term or phrase to look up, e.g. \"倍率\" or \"token group\".",
"maxLength": 160,
"type": "string"
},
"skillBuild": {
"description": "Grandet Skill build ID when called from the Skill. Omit otherwise.",
"maxLength": 256,
"type": "string"
},
"skillVersion": {
"description": "Grandet Skill version when called from the Skill, e.g. \"0.3.0\". Omit otherwise.",
"maxLength": 32,
"type": "string"
},
"targetApp": {
"description": "Catalogue ID of the app that will use the API, e.g. \"openclaw\", \"claude-code\" or \"codex\". Selects compatible protocols and connection steps. Send it only when the user says where the API will be used.",
"pattern": "^[a-zA-Z0-9._/-]{1,64}$",
"type": "string"
}
},
"type": "object"
},
"name": "grandet_glossary"
},
{
"description": "Read the shared Grandet application list and inference profiles before selecting a supplier. App profiles determine API compatibility; MCP capability alone does not prove an inference route or Skill installation. Use only when the target app ID, supported protocol or configuration variant is uncertain.",
"inputSchema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"additionalProperties": false,
"properties": {
"app": {
"description": "Catalogue app ID to show, e.g. \"openclaw\". Omit to list every app.",
"pattern": "^[a-zA-Z0-9._/-]{1,64}$",
"type": "string"
},
"host": {
"description": "The assistant or app making this call, e.g. \"claude-code\" or \"codex\". Attribution only; it does not change results.",
"pattern": "^[a-zA-Z0-9._/-]{1,64}$",
"type": "string"
},
"lang": {
"default": "en",
"description": "Answer language: \"en\" or \"zh-CN\".",
"enum": [
"en",
"zh-CN"
],
"type": "string"
},
"skillBuild": {
"description": "Grandet Skill build ID when called from the Skill. Omit otherwise.",
"maxLength": 256,
"type": "string"
},
"skillVersion": {
"description": "Grandet Skill version when called from the Skill, e.g. \"0.3.0\". Omit otherwise.",
"maxLength": 32,
"type": "string"
},
"targetApp": {
"description": "Catalogue ID of the app that will use the API, e.g. \"openclaw\", \"claude-code\" or \"codex\". Selects compatible protocols and connection steps. Send it only when the user says where the API will be used.",
"pattern": "^[a-zA-Z0-9._/-]{1,64}$",
"type": "string"
}
},
"type": "object"
},
"name": "grandet_list_apps"
},
{
"description": "Read one provider's paged public declarations for a model and optional rowId. Use only when a detail matters, not before every recommendation. A missing row on one page is not proof of absence; follow pagination if needed. This does not test model quality or spend money.",
"inputSchema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"additionalProperties": false,
"properties": {
"asOf": {
"description": "Evaluate as of this UTC time (ISO 8601, e.g. \"2026-10-16T12:00:00Z\"). Omit to evaluate now.",
"maxLength": 256,
"minLength": 1,
"type": "string"
},
"host": {
"description": "The assistant or app making this call, e.g. \"claude-code\" or \"codex\". Attribution only; it does not change results.",
"pattern": "^[a-zA-Z0-9._/-]{1,64}$",
"type": "string"
},
"lang": {
"default": "en",
"description": "Answer language: \"en\" or \"zh-CN\".",
"enum": [
"en",
"zh-CN"
],
"type": "string"
},
"model": {
"description": "Model to look up: a catalogue ID, an exact model name or a natural name such as \"claude-sonnet-5-5\". Send exactly one of model or name. An ambiguous name returns NEEDS_CLARIFICATION with candidates.",
"maxLength": 256,
"minLength": 1,
"type": "string"
},
"name": {
"description": "The catalogue's 20-character hexadecimal raw-name ID (not the name text). Send exactly one of model or name.",
"maxLength": 256,
"minLength": 1,
"type": "string"
},
"offerPage": {
"default": 1,
"description": "Page of this provider's declarations, starting at 1. Follow it when rowId is absent.",
"minimum": 1,
"type": "integer"
},
"provider": {
"description": "The sourceId of the row to inspect (the site host, e.g. \"api.example.com\"), not the operator ID.",
"maxLength": 256,
"minLength": 1,
"type": "string"
},
"releaseSet": {
"description": "Pin a published data release by its release-set hash. Omit to use the current release.",
"maxLength": 256,
"minLength": 1,
"type": "string"
},
"rowId": {
"description": "The rowId of the selected row, to read that exact declaration.",
"maxLength": 512,
"type": "string"
},
"skillBuild": {
"description": "Grandet Skill build ID when called from the Skill. Omit otherwise.",
"maxLength": 256,
"type": "string"
},
"skillVersion": {
"description": "Grandet Skill version when called from the Skill, e.g. \"0.3.0\". Omit otherwise.",
"maxLength": 32,
"type": "string"
},
"targetApp": {
"description": "Catalogue ID of the app that will use the API, e.g. \"openclaw\", \"claude-code\" or \"codex\". Selects compatible protocols and connection steps. Send it only when the user says where the API will be used.",
"pattern": "^[a-zA-Z0-9._/-]{1,64}$",
"type": "string"
}
},
"required": [
"provider"
],
"type": "object"
},
"name": "grandet_quote_evidence"
},
{
"description": "Look up public model identifiers when a requested name is ambiguous. Results are a page of candidates, not a cheapest-provider ranking. Prefer an exact officialId match; do not silently substitute a different model generation.",
"inputSchema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"additionalProperties": false,
"properties": {
"host": {
"description": "The assistant or app making this call, e.g. \"claude-code\" or \"codex\". Attribution only; it does not change results.",
"pattern": "^[a-zA-Z0-9._/-]{1,64}$",
"type": "string"
},
"lang": {
"default": "en",
"description": "Answer language: \"en\" or \"zh-CN\".",
"enum": [
"en",
"zh-CN"
],
"type": "string"
},
"name": {
"description": "Model name text to look up, e.g. \"sonnet\" or \"deepseek v4\".",
"maxLength": 256,
"minLength": 1,
"type": "string"
},
"page": {
"default": 1,
"description": "Result page, starting at 1.",
"minimum": 1,
"type": "integer"
},
"skillBuild": {
"description": "Grandet Skill build ID when called from the Skill. Omit otherwise.",
"maxLength": 256,
"type": "string"
},
"skillVersion": {
"description": "Grandet Skill version when called from the Skill, e.g. \"0.3.0\". Omit otherwise.",
"maxLength": 32,
"type": "string"
},
"targetApp": {
"description": "Catalogue ID of the app that will use the API, e.g. \"openclaw\", \"claude-code\" or \"codex\". Selects compatible protocols and connection steps. Send it only when the user says where the API will be used.",
"pattern": "^[a-zA-Z0-9._/-]{1,64}$",
"type": "string"
}
},
"required": [
"name"
],
"type": "object"
},
"name": "grandet_resolve_model"
}
]
}What the leaf hashes
{"body":"3b18906c5ee2e64b245073eb5c06cbc531e578125b895937af042900ff175dc2","id":221924,"kind":"mcp.tools","method":"probe.mcp/1","observed_us":1793027705635780,"prev":null,"subject":"a3fc06d8-2cc8-4508-acdd-0f4cc754e92a","subject_kind":"endpoint"}Proof
Fold these into the leaf in order, hashing each sorted pair with keccak256, to reach the root of (296695 rows).
- 0x17689e743f2a30979a48acbc91dd284bf6934dc465ab523690e80a5547f9cfd7
- 0x729bd0efc0b5e2573166777c0399977c6fcab05acc6f3462f7394a4eb8b15e7f
- 0x07c7dcb667967ca62b66a4725e796ef8661fc63d6e00b1329a4c0515ce42fc54
- 0x0a5c91cca36cf7ed58d7617a4dfba6d7260b519206b38ef5df85560953b241eb
- 0xc059acd76b6ae1c0e5c2c7d43ef6aabf5654764bb4ca5480fb79d9c522d76f93
- 0xcb2d8b863cb2ab18b961cd1173bdaa4e6b7dc613fb018c875655edc01c497f8c
- 0x21d08c95548ff7fc14b5b5016a46e51fa877331dfd3e7ca7ac6db6249d964352
- 0x12ac9abca55af0b3837c8f618f21f5f3040e5461ea53a7fbbdccd3eef12e7a0d
- 0x4e70f5f2f3c203f12709ed0c0f41607134188ecfceb56b8eaa6f6cae8620cede
- 0x0d4fc8ebd9dad99184207670597ef1933fa15a1f2659bf0e662e21ebef5f0e51
- 0x84d28434d4d3c4d17b89916035448fc07d9ad132609b14e307edbe020e19d1a6
- 0x15eab8feed5b3f08165d63b9f1aed508c0624966a05349e051f86f0c188707b5
- 0x32f46c5f73ecbfd4f770f7f760a79bee2afed4b3e7572fa882b3e7dce8df4356
- 0x770e4376196188c7fc9ec40f8e218dc0d1cb92bba5fe0425a0edce27ca9a997f
- 0x60582ab4b41e72eb70eb0bce07fbf0fb4d2b62a8bad5be50f5d16d511adc746c
- 0xc6a4d7899a0f442958e26505011190b7cff2483611c1b94eba9043e0ba9ac36e
- 0x8c756542e482157df0c36464d75c937b845e4423dbbcfad08f0cf8d5a16b9a13
- 0x20704208aa6923d6b2450ef74ede87a6e0265d46447926038fe9506e9e154b2d
- 0x9b9ce5b74b9bab5121612ef6b64920a8d453cbf311096a423eef9702747e868a
- Day root
- 0xf43e8dcc3d451a4788b26be904c55e8c4c0fa75c9666796c51db38d37e2c0df8
- Chained
- 0x702d5ac508f08b0d1accf36af25822d8e5660367494edd17a642fb61e158a57a
- Published
- On Arc Testnet, block 69251483: 0x495162f8936e19f0039918feebe6c307f327cd6bf8c37219620b1970041fa9ae