Santismm Knowledge — Harness Engineering, Agentic AI & Governance
Query core AI knowledge, essays, executable Labs, Homeric data and epistemic claims.
使うべきか
品質と安全性
A
検出事項（2）
- LOWTool 'calculate_evaluation_sample_size' name length outside 3-30 rangecalculate_evaluation_sample_size 内
- LOWTool 'calculate_human_supervision_capacity' name length outside 3-30 rangecalculate_human_supervision_capacity 内
ツール定義とプロトコルへの準拠に関する自動分析に基づいています。
コンテキストコスト
~14,707トークン数（ツール定義）
~4.9 KB一般的なレスポンスサイズ
注意への影響は大きい（128k コンテキストの 11.49%）
これは、サーバーのツールがモデルのコンテキストに読み込まれるたびに消費されるおおよそのトークン数です。数が多いほど、ほかのタスクに使える注意が減ります。
インストール
ワンクリックインストール
これを `claude_desktop_config.json` ファイルに追加してください:
{
"mcpServers": {
"knowledge": {
"url": "https://santismm.com/mcp"
}
}
}リモートエンドポイント
https://santismm.com/mcpstreamable-httpできること
ツール一覧
ツール（30）
🟢 読み取り専用🟡 書き込み🔴 削除⚪ 不明
🟢get_overview
Get the complete MCP map — start here. Returns the five-domain core plus the separate Article, Labs, Homeric Atlas and claim-registry surfaces, with their tools, identifiers, citation rules, languages, licence and bulk-ingest URLs.
入力スキーマ
{
"type": "object",
"properties": {},
"$schema": "https://json-schema.org/draft/2020-12/schema"
}出力スキーマ
{
"type": "object",
"properties": {
"resource_uri": {
"type": "string",
"description": "Read this same document with resources/read."
},
"source": {
"type": "string"
},
"site": {
"type": "string"
},
"locales": {
"type": "array",
"items": {
"type": "string"
}
},
"license": {
"type": "string"
},
"license_spdx": {
"type": "string",
"description": "SPDX id — check this, not the prose."
},
"license_url": {
"type": "string"
},
"total": {
"type": "number"
},
"domains": {
"type": "array",
"items": {
"type": "object",
"properties": {
"domain": {
"type": "string"
},
"count": {
"type": "number"
},
"description": {
"type": "string"
},
"categories": {
"type": "array",
"items": {
"type": "string"
}
},
"tools": {
"type": "object",
"properties": {
"list": {
"type": "string"
},
"get": {
"type": "string"
}
},
"required": [
"list",
"get"
],
"additionalProperties": false
},
"lookup": {
"type": "string"
},
"url": {
"type": "string"
},
"api_url": {
"type": "string"
}
},
"required": [
"domain",
"count",
"description",
"categories",
"tools",
"lookup",
"url",
"api_url"
],
"additionalProperties": false
}
},
"extensions": {
"type": "array",
"items": {
"type": "object",
"properties": {
"surface": {
"type": "string"
},
"description": {
"type": "string"
},
"tools": {
"type": "array",
"items": {
"type": "string"
}
},
"source": {
"type": "string"
},
"lookup": {
"type": "string"
},
"citation": {
"type": "string"
}
},
"required": [
"surface",
"description",
"tools",
"source",
"lookup",
"citation"
],
"additionalProperties": false
}
},
"corpus": {
"type": "object",
"properties": {
"newest_unit": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "Newest unit date in THIS copy (YYYY-MM-DD)."
},
"freshness": {
"type": "string"
}
},
"required": [
"newest_unit",
"freshness"
],
"additionalProperties": false,
"description": "Whether this copy is current. Compare against the hosted endpoint: a lower total or an older newest_unit means you are holding a snapshot, not that the corpus lacks what you asked for."
},
"next": {
"type": "string"
},
"bulk": {
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {
"type": "string"
}
}
},
"required": [
"resource_uri",
"source",
"site",
"locales",
"license",
"license_spdx",
"license_url",
"total",
"domains",
"extensions",
"corpus",
"next",
"bulk"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false
}🟢search_all(query, surfaces, limit_per_surface, locale)
Search the core corpus, first-party essays, executable Labs, epistemic claims and the Homeric Atlas in one call. Use this first when a natural-language question might require a calculation, a long-form essay or a claim audit rather than only a core knowledge unit. Results name the next tool to call; calculator-shaped questions are routed toward Labs.
入力スキーマ
{
"type": "object",
"properties": {
"query": {
"type": "string",
"minLength": 1,
"maxLength": 512,
"description": "Question or topic, in English, Spanish, Portuguese, French, German, Japanese or Simplified Chinese."
},
"surfaces": {
"description": "Restrict the search. Omit to search all five surfaces.",
"minItems": 1,
"type": "array",
"items": {
"type": "string",
"enum": [
"core",
"articles",
"labs",
"claims",
"homeric_atlas"
]
}
},
"limit_per_surface": {
"description": "Maximum hits from each surface. Default: 5.",
"type": "integer",
"exclusiveMinimum": 0,
"maximum": 10
},
"locale": {
"description": "Language of the returned body. Default: en.",
"type": "string",
"enum": [
"en",
"es",
"pt",
"fr",
"de",
"ja",
"zh"
]
}
},
"required": [
"query"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}出力スキーマ
{
"type": "object",
"properties": {
"query": {
"type": "string"
},
"count": {
"type": "number"
},
"results": {
"type": "array",
"items": {
"type": "object",
"properties": {
"surface": {
"type": "string",
"enum": [
"core",
"articles",
"labs",
"claims",
"homeric_atlas"
]
},
"score": {
"type": "number"
},
"source_score": {
"type": "number"
},
"rank_within_surface": {
"type": "number"
},
"id": {
"type": "string"
},
"slug": {
"type": "string"
},
"domain": {
"type": "string"
},
"kind": {
"type": "string"
},
"title": {
"type": "string"
},
"summary": {
"type": "string"
},
"canonical_url": {
"type": "string"
},
"api_url": {
"type": "string"
},
"calculation_url": {
"type": "string"
},
"suggested_tool": {
"type": "string"
},
"matchedFields": {
"type": "array",
"items": {
"type": "string"
}
},
"matchedTerms": {
"type": "array",
"items": {
"type": "string"
}
}
},
"required": [
"surface",
"score",
"source_score",
"rank_within_surface",
"slug",
"title",
"suggested_tool",
"matchedFields",
"matchedTerms"
],
"additionalProperties": {}
}
},
"unavailable_surfaces": {
"type": "array",
"items": {
"type": "object",
"properties": {
"surface": {
"type": "string",
"enum": [
"articles",
"labs"
]
},
"error": {
"type": "string"
},
"retry_tool": {
"type": "string"
}
},
"required": [
"surface",
"error",
"retry_tool"
],
"additionalProperties": false
}
}
},
"required": [
"query",
"count",
"results",
"unavailable_surfaces"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false
}🟢list_knowledge(locale)
List all knowledge units (concepts on agentic & enterprise AI) with slug, category, title, summary and Evidence-First provenance. Use this to browse the domain; use `search` when you have a question rather than a slug.
入力スキーマ
{
"type": "object",
"properties": {
"locale": {
"description": "Language of the returned body. Default: en.",
"type": "string",
"enum": [
"en",
"es",
"pt",
"fr",
"de",
"ja",
"zh"
]
}
},
"$schema": "https://json-schema.org/draft/2020-12/schema"
}出力スキーマ
{
"type": "object",
"properties": {
"count": {
"type": "number"
},
"results": {
"type": "array",
"items": {
"type": "object",
"properties": {
"domain": {
"type": "string"
},
"id": {
"type": "string"
},
"slug": {
"type": "string"
},
"category": {
"type": "string"
},
"name": {
"type": "string"
},
"summary": {
"type": "string"
},
"status": {
"type": "string"
},
"evidence": {
"description": "Evidence-First provenance: weight claims by this.",
"type": "object",
"properties": {
"evidenceLevel": {
"type": "string"
},
"confidenceLevel": {
"type": "string"
},
"sourceType": {
"type": "array",
"items": {
"type": "string"
}
}
},
"additionalProperties": false
},
"updated": {
"type": "string"
},
"locale": {
"type": "string"
},
"canonical_url": {
"description": "Cite this URL.",
"type": "string"
},
"api_url": {
"type": "string"
},
"resource_uri": {
"description": "Read this card as an MCP Resource.",
"type": "string"
}
},
"required": [
"domain",
"slug",
"name"
],
"additionalProperties": {}
}
}
},
"required": [
"count",
"results"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false
}🟢get_knowledge(slug, locale)
Get one knowledge unit by slug. Returns the full entry, or a single-locale body if locale is given. Use this once `search` or `list_knowledge` has given you a slug.
入力スキーマ
{
"type": "object",
"properties": {
"slug": {
"type": "string",
"minLength": 1,
"maxLength": 128,
"description": "Knowledge unit slug, e.g. 'harness-engineering'."
},
"locale": {
"description": "Language of the returned body. Default: en.",
"type": "string",
"enum": [
"en",
"es",
"pt",
"fr",
"de",
"ja",
"zh"
]
}
},
"required": [
"slug"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}出力スキーマ
{
"type": "object",
"properties": {
"domain": {
"type": "string"
},
"id": {
"type": "string"
},
"slug": {
"type": "string"
},
"aliases": {
"type": "array",
"items": {
"type": "string"
}
},
"category": {
"type": "string"
},
"updated": {
"type": "string"
},
"version": {
"type": "string"
},
"locale": {
"type": "string"
},
"evidence": {
"description": "Evidence-First provenance: weight claims by this.",
"type": "object",
"properties": {
"evidenceLevel": {
"type": "string"
},
"confidenceLevel": {
"type": "string"
},
"sourceType": {
"type": "array",
"items": {
"type": "string"
}
}
},
"additionalProperties": false
},
"canonical_url": {
"type": "string"
},
"api_url": {
"type": "string"
},
"resource_uri": {
"type": "string"
},
"references": {
"type": "array",
"items": {
"type": "object",
"properties": {
"title": {
"type": "string"
},
"url": {
"type": "string"
}
},
"additionalProperties": false
}
},
"featured": {
"type": "boolean"
},
"related": {
"type": "array",
"items": {
"type": "string"
}
},
"patterns": {
"type": "array",
"items": {
"type": "string"
}
},
"knowledge": {
"type": "array",
"items": {
"type": "string"
}
},
"frameworks": {
"type": "array",
"items": {
"type": "string"
}
},
"technologies": {
"type": "array",
"items": {
"type": "string"
}
},
"tags": {
"type": "array",
"items": {
"type": "string"
}
},
"locales": {
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {}
},
"body": {},
"requested_locale": {
"type": "string"
},
"resolved_locale": {
"type": "string"
},
"fallback": {
"type": "boolean"
},
"status": {
"type": "string"
},
"name": {
"type": "string"
},
"summary": {
"type": "string"
}
},
"required": [
"domain",
"slug",
"category",
"updated",
"version",
"evidence",
"canonical_url",
"api_url",
"references",
"related"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false
}🟢list_patterns(locale)
List all Enterprise AI patterns (reusable agentic design patterns) with slug, category, name, summary and provenance. Use this to browse the catalogue; use `search` when you are looking for a pattern that solves a problem.
入力スキーマ
{
"type": "object",
"properties": {
"locale": {
"description": "Language of the returned body. Default: en.",
"type": "string",
"enum": [
"en",
"es",
"pt",
"fr",
"de",
"ja",
"zh"
]
}
},
"$schema": "https://json-schema.org/draft/2020-12/schema"
}出力スキーマ
{
"type": "object",
"properties": {
"count": {
"type": "number"
},
"results": {
"type": "array",
"items": {
"type": "object",
"properties": {
"domain": {
"type": "string"
},
"id": {
"type": "string"
},
"slug": {
"type": "string"
},
"category": {
"type": "string"
},
"name": {
"type": "string"
},
"summary": {
"type": "string"
},
"status": {
"type": "string"
},
"evidence": {
"description": "Evidence-First provenance: weight claims by this.",
"type": "object",
"properties": {
"evidenceLevel": {
"type": "string"
},
"confidenceLevel": {
"type": "string"
},
"sourceType": {
"type": "array",
"items": {
"type": "string"
}
}
},
"additionalProperties": false
},
"updated": {
"type": "string"
},
"locale": {
"type": "string"
},
"canonical_url": {
"description": "Cite this URL.",
"type": "string"
},
"api_url": {
"type": "string"
},
"resource_uri": {
"description": "Read this card as an MCP Resource.",
"type": "string"
}
},
"required": [
"domain",
"slug",
"name"
],
"additionalProperties": {}
}
}
},
"required": [
"count",
"results"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false
}🟢get_pattern(slug, locale)
Get one Enterprise AI pattern by slug (includes problem, solution, KPIs, failure modes, lessons). Use this once `search` or `list_patterns` has given you a slug.
入力スキーマ
{
"type": "object",
"properties": {
"slug": {
"type": "string",
"minLength": 1,
"maxLength": 128,
"description": "Pattern slug, e.g. 'human-approval-gate'."
},
"locale": {
"description": "Language of the returned body. Default: en.",
"type": "string",
"enum": [
"en",
"es",
"pt",
"fr",
"de",
"ja",
"zh"
]
}
},
"required": [
"slug"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}出力スキーマ
{
"type": "object",
"properties": {
"domain": {
"type": "string"
},
"id": {
"type": "string"
},
"slug": {
"type": "string"
},
"aliases": {
"type": "array",
"items": {
"type": "string"
}
},
"category": {
"type": "string"
},
"updated": {
"type": "string"
},
"version": {
"type": "string"
},
"locale": {
"type": "string"
},
"evidence": {
"description": "Evidence-First provenance: weight claims by this.",
"type": "object",
"properties": {
"evidenceLevel": {
"type": "string"
},
"confidenceLevel": {
"type": "string"
},
"sourceType": {
"type": "array",
"items": {
"type": "string"
}
}
},
"additionalProperties": false
},
"canonical_url": {
"type": "string"
},
"api_url": {
"type": "string"
},
"resource_uri": {
"type": "string"
},
"references": {
"type": "array",
"items": {
"type": "object",
"properties": {
"title": {
"type": "string"
},
"url": {
"type": "string"
}
},
"additionalProperties": false
}
},
"featured": {
"type": "boolean"
},
"related": {
"type": "array",
"items": {
"type": "string"
}
},
"patterns": {
"type": "array",
"items": {
"type": "string"
}
},
"knowledge": {
"type": "array",
"items": {
"type": "string"
}
},
"frameworks": {
"type": "array",
"items": {
"type": "string"
}
},
"technologies": {
"type": "array",
"items": {
"type": "string"
}
},
"tags": {
"type": "array",
"items": {
"type": "string"
}
},
"locales": {
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {}
},
"body": {},
"requested_locale": {
"type": "string"
},
"resolved_locale": {
"type": "string"
},
"fallback": {
"type": "boolean"
},
"status": {
"type": "string"
},
"name": {
"type": "string"
},
"summary": {
"type": "string"
}
},
"required": [
"domain",
"slug",
"category",
"updated",
"version",
"evidence",
"canonical_url",
"api_url",
"references",
"related"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false
}🟢list_architectures(locale)
List all reference architectures (end-to-end enterprise agentic blueprints) with id, slug, category, name, summary and provenance. Use this to browse the blueprints; use `search` when you have a use case rather than a name.
入力スキーマ
{
"type": "object",
"properties": {
"locale": {
"description": "Language of the returned body. Default: en.",
"type": "string",
"enum": [
"en",
"es",
"pt",
"fr",
"de",
"ja",
"zh"
]
}
},
"$schema": "https://json-schema.org/draft/2020-12/schema"
}出力スキーマ
{
"type": "object",
"properties": {
"count": {
"type": "number"
},
"results": {
"type": "array",
"items": {
"type": "object",
"properties": {
"domain": {
"type": "string"
},
"id": {
"type": "string"
},
"slug": {
"type": "string"
},
"category": {
"type": "string"
},
"name": {
"type": "string"
},
"summary": {
"type": "string"
},
"status": {
"type": "string"
},
"evidence": {
"description": "Evidence-First provenance: weight claims by this.",
"type": "object",
"properties": {
"evidenceLevel": {
"type": "string"
},
"confidenceLevel": {
"type": "string"
},
"sourceType": {
"type": "array",
"items": {
"type": "string"
}
}
},
"additionalProperties": false
},
"updated": {
"type": "string"
},
"locale": {
"type": "string"
},
"canonical_url": {
"description": "Cite this URL.",
"type": "string"
},
"api_url": {
"type": "string"
},
"resource_uri": {
"description": "Read this card as an MCP Resource.",
"type": "string"
}
},
"required": [
"domain",
"slug",
"name"
],
"additionalProperties": {}
}
}
},
"required": [
"count",
"results"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false
}🟢get_architecture(slug, locale)
Get one reference architecture by slug (includes the request flow, reference scenario, KPIs, cost & scaling, and the patterns/knowledge it composes). Use this once `search` or `list_architectures` has given you a slug.
入力スキーマ
{
"type": "object",
"properties": {
"slug": {
"type": "string",
"minLength": 1,
"maxLength": 128,
"description": "Architecture slug, e.g. 'customer-service-agent'."
},
"locale": {
"description": "Language of the returned body. Default: en.",
"type": "string",
"enum": [
"en",
"es",
"pt",
"fr",
"de",
"ja",
"zh"
]
}
},
"required": [
"slug"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}出力スキーマ
{
"type": "object",
"properties": {
"domain": {
"type": "string"
},
"id": {
"type": "string"
},
"slug": {
"type": "string"
},
"aliases": {
"type": "array",
"items": {
"type": "string"
}
},
"category": {
"type": "string"
},
"updated": {
"type": "string"
},
"version": {
"type": "string"
},
"locale": {
"type": "string"
},
"evidence": {
"description": "Evidence-First provenance: weight claims by this.",
"type": "object",
"properties": {
"evidenceLevel": {
"type": "string"
},
"confidenceLevel": {
"type": "string"
},
"sourceType": {
"type": "array",
"items": {
"type": "string"
}
}
},
"additionalProperties": false
},
"canonical_url": {
"type": "string"
},
"api_url": {
"type": "string"
},
"resource_uri": {
"type": "string"
},
"references": {
"type": "array",
"items": {
"type": "object",
"properties": {
"title": {
"type": "string"
},
"url": {
"type": "string"
}
},
"additionalProperties": false
}
},
"featured": {
"type": "boolean"
},
"related": {
"type": "array",
"items": {
"type": "string"
}
},
"patterns": {
"type": "array",
"items": {
"type": "string"
}
},
"knowledge": {
"type": "array",
"items": {
"type": "string"
}
},
"frameworks": {
"type": "array",
"items": {
"type": "string"
}
},
"technologies": {
"type": "array",
"items": {
"type": "string"
}
},
"tags": {
"type": "array",
"items": {
"type": "string"
}
},
"locales": {
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {}
},
"body": {},
"requested_locale": {
"type": "string"
},
"resolved_locale": {
"type": "string"
},
"fallback": {
"type": "boolean"
},
"status": {
"type": "string"
},
"name": {
"type": "string"
},
"summary": {
"type": "string"
}
},
"required": [
"domain",
"slug",
"category",
"updated",
"version",
"evidence",
"canonical_url",
"api_url",
"references",
"related"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false
}🟢list_governance(locale)
List all AI governance units (regulations, standards, frameworks, playbooks — EU AI Act, ISO 42001, NIST AI RMF, agentic checklist) with id, slug, category, name and summary. Use this to browse the regulations and standards; use `search` for an obligation or control.
入力スキーマ
{
"type": "object",
"properties": {
"locale": {
"description": "Language of the returned body. Default: en.",
"type": "string",
"enum": [
"en",
"es",
"pt",
"fr",
"de",
"ja",
"zh"
]
}
},
"$schema": "https://json-schema.org/draft/2020-12/schema"
}出力スキーマ
{
"type": "object",
"properties": {
"count": {
"type": "number"
},
"results": {
"type": "array",
"items": {
"type": "object",
"properties": {
"domain": {
"type": "string"
},
"id": {
"type": "string"
},
"slug": {
"type": "string"
},
"category": {
"type": "string"
},
"name": {
"type": "string"
},
"summary": {
"type": "string"
},
"status": {
"type": "string"
},
"evidence": {
"description": "Evidence-First provenance: weight claims by this.",
"type": "object",
"properties": {
"evidenceLevel": {
"type": "string"
},
"confidenceLevel": {
"type": "string"
},
"sourceType": {
"type": "array",
"items": {
"type": "string"
}
}
},
"additionalProperties": false
},
"updated": {
"type": "string"
},
"locale": {
"type": "string"
},
"canonical_url": {
"description": "Cite this URL.",
"type": "string"
},
"api_url": {
"type": "string"
},
"resource_uri": {
"description": "Read this card as an MCP Resource.",
"type": "string"
}
},
"required": [
"domain",
"slug",
"name"
],
"additionalProperties": {}
}
}
},
"required": [
"count",
"results"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false
}🟢get_governance(slug, locale)
Get one AI governance unit by slug (includes scope, key requirements, implementable controls, a checklist and common pitfalls). Use this once `search` or `list_governance` has given you a slug.
入力スキーマ
{
"type": "object",
"properties": {
"slug": {
"type": "string",
"minLength": 1,
"maxLength": 128,
"description": "Governance unit slug, e.g. 'eu-ai-act'."
},
"locale": {
"description": "Language of the returned body. Default: en.",
"type": "string",
"enum": [
"en",
"es",
"pt",
"fr",
"de",
"ja",
"zh"
]
}
},
"required": [
"slug"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}出力スキーマ
{
"type": "object",
"properties": {
"domain": {
"type": "string"
},
"id": {
"type": "string"
},
"slug": {
"type": "string"
},
"aliases": {
"type": "array",
"items": {
"type": "string"
}
},
"category": {
"type": "string"
},
"updated": {
"type": "string"
},
"version": {
"type": "string"
},
"locale": {
"type": "string"
},
"evidence": {
"description": "Evidence-First provenance: weight claims by this.",
"type": "object",
"properties": {
"evidenceLevel": {
"type": "string"
},
"confidenceLevel": {
"type": "string"
},
"sourceType": {
"type": "array",
"items": {
"type": "string"
}
}
},
"additionalProperties": false
},
"canonical_url": {
"type": "string"
},
"api_url": {
"type": "string"
},
"resource_uri": {
"type": "string"
},
"references": {
"type": "array",
"items": {
"type": "object",
"properties": {
"title": {
"type": "string"
},
"url": {
"type": "string"
}
},
"additionalProperties": false
}
},
"featured": {
"type": "boolean"
},
"related": {
"type": "array",
"items": {
"type": "string"
}
},
"patterns": {
"type": "array",
"items": {
"type": "string"
}
},
"knowledge": {
"type": "array",
"items": {
"type": "string"
}
},
"frameworks": {
"type": "array",
"items": {
"type": "string"
}
},
"technologies": {
"type": "array",
"items": {
"type": "string"
}
},
"tags": {
"type": "array",
"items": {
"type": "string"
}
},
"locales": {
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {}
},
"body": {},
"requested_locale": {
"type": "string"
},
"resolved_locale": {
"type": "string"
},
"fallback": {
"type": "boolean"
},
"status": {
"type": "string"
},
"name": {
"type": "string"
},
"summary": {
"type": "string"
}
},
"required": [
"domain",
"slug",
"category",
"updated",
"version",
"evidence",
"canonical_url",
"api_url",
"references",
"related"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false
}🟢list_handbook(locale)
List the Harness Engineering Handbook chapters (HRN-001…): the canonical long-form corpus on harness engineering — definition, history, taxonomy, principles, memory, observability, evaluation, governance, planning, orchestration, security, case studies, glossary and bibliography. Use this to see the chapter map; use `search` when you have a topic rather than a chapter.
入力スキーマ
{
"type": "object",
"properties": {
"locale": {
"description": "Language of the returned body. Default: en.",
"type": "string",
"enum": [
"en",
"es",
"pt",
"fr",
"de",
"ja",
"zh"
]
}
},
"$schema": "https://json-schema.org/draft/2020-12/schema"
}出力スキーマ
{
"type": "object",
"properties": {
"count": {
"type": "number"
},
"results": {
"type": "array",
"items": {
"type": "object",
"properties": {
"domain": {
"type": "string"
},
"id": {
"type": "string"
},
"slug": {
"type": "string"
},
"category": {
"type": "string"
},
"name": {
"type": "string"
},
"summary": {
"type": "string"
},
"status": {
"type": "string"
},
"evidence": {
"description": "Evidence-First provenance: weight claims by this.",
"type": "object",
"properties": {
"evidenceLevel": {
"type": "string"
},
"confidenceLevel": {
"type": "string"
},
"sourceType": {
"type": "array",
"items": {
"type": "string"
}
}
},
"additionalProperties": false
},
"updated": {
"type": "string"
},
"locale": {
"type": "string"
},
"canonical_url": {
"description": "Cite this URL.",
"type": "string"
},
"api_url": {
"type": "string"
},
"resource_uri": {
"description": "Read this card as an MCP Resource.",
"type": "string"
}
},
"required": [
"domain",
"slug",
"name"
],
"additionalProperties": {}
}
}
},
"required": [
"count",
"results"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false
}🟢get_handbook(id, locale)
Get one Harness Engineering Handbook chapter, by id (e.g. 'HRN-001') or slug. Returns the full Markdown body plus its provenance and related ids. Use this once `search` or `list_handbook` has given you an id.
入力スキーマ
{
"type": "object",
"properties": {
"id": {
"type": "string",
"minLength": 1,
"maxLength": 128,
"description": "Chapter id like 'HRN-001', or its slug."
},
"locale": {
"description": "Language of the returned body. Default: en.",
"type": "string",
"enum": [
"en",
"es",
"pt",
"fr",
"de",
"ja",
"zh"
]
}
},
"required": [
"id"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}出力スキーマ
{
"type": "object",
"properties": {
"domain": {
"type": "string"
},
"id": {
"type": "string"
},
"slug": {
"type": "string"
},
"aliases": {
"type": "array",
"items": {
"type": "string"
}
},
"category": {
"type": "string"
},
"updated": {
"type": "string"
},
"version": {
"type": "string"
},
"locale": {
"type": "string"
},
"evidence": {
"description": "Evidence-First provenance: weight claims by this.",
"type": "object",
"properties": {
"evidenceLevel": {
"type": "string"
},
"confidenceLevel": {
"type": "string"
},
"sourceType": {
"type": "array",
"items": {
"type": "string"
}
}
},
"additionalProperties": false
},
"canonical_url": {
"type": "string"
},
"api_url": {
"type": "string"
},
"resource_uri": {
"type": "string"
},
"references": {
"type": "array",
"items": {
"type": "object",
"properties": {
"title": {
"type": "string"
},
"url": {
"type": "string"
}
},
"additionalProperties": false
}
},
"featured": {
"type": "boolean"
},
"related": {
"type": "array",
"items": {
"type": "string"
}
},
"patterns": {
"type": "array",
"items": {
"type": "string"
}
},
"knowledge": {
"type": "array",
"items": {
"type": "string"
}
},
"frameworks": {
"type": "array",
"items": {
"type": "string"
}
},
"technologies": {
"type": "array",
"items": {
"type": "string"
}
},
"tags": {
"type": "array",
"items": {
"type": "string"
}
},
"locales": {
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {}
},
"body": {
"description": "Full Markdown body of the chapter.",
"type": "string"
},
"requested_locale": {
"description": "The locale that was asked for.",
"type": "string"
},
"resolved_locale": {
"description": "The locale actually returned. Chapters are authored in English and translated; where a translation exists this equals the requested locale, and `fallback` says when it does not.",
"type": "string"
},
"fallback": {
"description": "True when the body is not in the requested locale.",
"type": "boolean"
},
"status": {
"type": "string"
},
"name": {
"type": "string"
},
"summary": {
"type": "string"
}
},
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": {}
}🟢search(query, domains, limit, locale)
Ranked keyword search across the whole corpus (knowledge, patterns, architectures, governance and the handbook). Matches every language and ignores accents, so query in the user's own words. Each hit carries a relevance score and the fields it matched; follow up with the matching get_* tool for full detail. Use this before any `get_*` tool whenever you have a question rather than an identifier.
入力スキーマ
{
"type": "object",
"properties": {
"query": {
"type": "string",
"minLength": 1,
"maxLength": 512,
"description": "Keyword or phrase to search for in any supported language."
},
"domains": {
"description": "Restrict to these domains. Omit to search everything, including the handbook.",
"type": "array",
"items": {
"type": "string",
"enum": [
"knowledge",
"patterns",
"architectures",
"governance",
"handbook"
]
}
},
"limit": {
"description": "Max results (default 20).",
"type": "integer",
"exclusiveMinimum": 0,
"maximum": 100
},
"locale": {
"description": "Language of the returned body. Default: en.",
"type": "string",
"enum": [
"en",
"es",
"pt",
"fr",
"de",
"ja",
"zh"
]
}
},
"required": [
"query"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}出力スキーマ
{
"type": "object",
"properties": {
"query": {
"type": "string"
},
"count": {
"type": "number"
},
"results": {
"type": "array",
"items": {
"type": "object",
"properties": {
"domain": {
"type": "string"
},
"id": {
"type": "string"
},
"slug": {
"type": "string"
},
"category": {
"type": "string"
},
"name": {
"type": "string"
},
"summary": {
"type": "string"
},
"status": {
"type": "string"
},
"evidence": {
"description": "Evidence-First provenance: weight claims by this.",
"type": "object",
"properties": {
"evidenceLevel": {
"type": "string"
},
"confidenceLevel": {
"type": "string"
},
"sourceType": {
"type": "array",
"items": {
"type": "string"
}
}
},
"additionalProperties": false
},
"updated": {
"type": "string"
},
"locale": {
"type": "string"
},
"canonical_url": {
"description": "Cite this URL.",
"type": "string"
},
"api_url": {
"type": "string"
},
"resource_uri": {
"description": "Read this card as an MCP Resource.",
"type": "string"
},
"score": {
"type": "number",
"description": "Relevance; higher is better."
},
"matchedFields": {
"type": "array",
"items": {
"type": "string"
},
"description": "Which fields the query hit."
},
"matchedTerms": {
"type": "array",
"items": {
"type": "string"
}
}
},
"required": [
"domain",
"slug",
"name",
"score",
"matchedFields",
"matchedTerms"
],
"additionalProperties": {}
}
}
},
"required": [
"query",
"count",
"results"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false
}🟢list_articles(locale)
List every long-form essay published on articles.santismm.com, with language, dates, topics and citable canonical URLs. Use this to browse the essay catalogue; use `search_articles` when you have a topic rather than a slug.
入力スキーマ
{
"type": "object",
"properties": {
"locale": {
"description": "Restrict by language. Articles are currently published in en, es and pt.",
"type": "string",
"enum": [
"en",
"es",
"pt",
"fr",
"de",
"ja",
"zh"
]
}
},
"$schema": "https://json-schema.org/draft/2020-12/schema"
}出力スキーマ
{
"type": "object",
"properties": {
"count": {
"type": "number"
},
"results": {
"type": "array",
"items": {
"type": "object",
"properties": {
"slug": {
"type": "string"
},
"title": {
"type": "string"
},
"summary": {
"type": "string"
},
"language": {
"type": "string"
},
"published": {
"type": "string"
},
"modified": {
"type": "string"
},
"topics": {
"type": "array",
"items": {
"type": "string"
}
},
"translation_key": {
"type": "string"
},
"canonical_url": {
"type": "string",
"description": "Cite this URL."
},
"api_url": {
"type": "string"
},
"resource_uri": {
"type": "string"
}
},
"required": [
"slug",
"title",
"summary",
"language",
"published",
"modified",
"topics",
"canonical_url",
"api_url",
"resource_uri"
],
"additionalProperties": false
}
}
},
"required": [
"count",
"results"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false
}🟢get_article(slug)
Get one complete essay by slug, including its clean Markdown-like body, metadata, licence context and canonical URL. Use this after `list_articles` or `search_articles` has returned the slug you need.
入力スキーマ
{
"type": "object",
"properties": {
"slug": {
"type": "string",
"minLength": 1,
"maxLength": 128,
"description": "Article slug, e.g. 'the-stopwatch-and-the-exam'."
}
},
"required": [
"slug"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}出力スキーマ
{
"type": "object",
"properties": {
"slug": {
"type": "string"
},
"title": {
"type": "string"
},
"summary": {
"type": "string"
},
"language": {
"type": "string"
},
"published": {
"type": "string"
},
"modified": {
"type": "string"
},
"topics": {
"type": "array",
"items": {
"type": "string"
}
},
"translation_key": {
"type": "string"
},
"canonical_url": {
"type": "string",
"description": "Cite this URL."
},
"api_url": {
"type": "string"
},
"resource_uri": {
"type": "string"
},
"body": {
"type": "string",
"description": "Full Markdown-like article body."
}
},
"required": [
"slug",
"title",
"summary",
"language",
"published",
"modified",
"topics",
"canonical_url",
"api_url",
"resource_uri",
"body"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false
}🟢search_articles(query, locale, limit)
Ranked, accent-insensitive full-text search over every first-party essay, including titles, summaries, topics and bodies. Use this when you need long-form analysis about a topic; follow with `get_article` for the complete essay.
入力スキーマ
{
"type": "object",
"properties": {
"query": {
"type": "string",
"minLength": 1,
"maxLength": 512,
"description": "Keyword or phrase to search for in any supported language."
},
"locale": {
"description": "Restrict by language. Articles are currently published in en, es and pt.",
"type": "string",
"enum": [
"en",
"es",
"pt",
"fr",
"de",
"ja",
"zh"
]
},
"limit": {
"description": "Maximum results (default 10).",
"type": "integer",
"exclusiveMinimum": 0,
"maximum": 20
}
},
"required": [
"query"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}出力スキーマ
{
"type": "object",
"properties": {
"query": {
"type": "string"
},
"count": {
"type": "number"
},
"results": {
"type": "array",
"items": {
"type": "object",
"properties": {
"slug": {
"type": "string"
},
"title": {
"type": "string"
},
"summary": {
"type": "string"
},
"language": {
"type": "string"
},
"published": {
"type": "string"
},
"modified": {
"type": "string"
},
"topics": {
"type": "array",
"items": {
"type": "string"
}
},
"translation_key": {
"type": "string"
},
"canonical_url": {
"type": "string",
"description": "Cite this URL."
},
"api_url": {
"type": "string"
},
"resource_uri": {
"type": "string"
},
"score": {
"type": "number"
},
"matchedFields": {
"type": "array",
"items": {
"type": "string"
}
},
"matchedTerms": {
"type": "array",
"items": {
"type": "string"
}
}
},
"required": [
"slug",
"title",
"summary",
"language",
"published",
"modified",
"topics",
"canonical_url",
"api_url",
"resource_uri",
"score",
"matchedFields",
"matchedTerms"
],
"additionalProperties": false
}
}
},
"required": [
"query",
"count",
"results"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false
}🟢list_labs(kind)
List every SANTISMM Lab with its inputs, outputs, assumptions, formulas and citation URL. Use this to discover interactive and machine-readable tools; filter by kind when the user specifically asks for a calculator, converter, experiment or educational game.
入力スキーマ
{
"type": "object",
"properties": {
"kind": {
"description": "Restrict results to one Lab kind. Omit to list every Lab.",
"type": "string",
"enum": [
"calculator",
"converter",
"experiment",
"educational-game"
]
}
},
"$schema": "https://json-schema.org/draft/2020-12/schema"
}出力スキーマ
{
"type": "object",
"properties": {
"count": {
"type": "number"
},
"results": {
"type": "array",
"items": {
"oneOf": [
{
"type": "object",
"properties": {
"executable": {
"type": "boolean",
"const": true
},
"owner_server": {
"type": "string",
"description": "Host that serves and versions this unit."
},
"slug": {
"type": "string"
},
"kind": {
"type": "string",
"enum": [
"calculator",
"converter",
"experiment",
"educational-game"
]
},
"label": {
"type": "string"
},
"title": {
"type": "string"
},
"description": {
"type": "string"
},
"inputs": {
"type": "array",
"items": {
"type": "string"
}
},
"outputs": {
"type": "array",
"items": {
"type": "string"
}
},
"formulas": {
"type": "array",
"items": {
"type": "string"
}
},
"assumptions": {
"type": "array",
"items": {
"type": "string"
}
},
"version": {
"type": "string"
},
"updated": {
"type": "string"
},
"canonical_url": {
"type": "string",
"description": "Cite this URL."
},
"api_url": {
"type": "string"
},
"calculation_url": {
"type": "string"
},
"related_content": {
"type": "array",
"items": {
"type": "object",
"properties": {
"title": {
"type": "string"
},
"url": {
"type": "string"
},
"relationship": {
"type": "string"
}
},
"required": [
"title",
"url",
"relationship"
],
"additionalProperties": false
}
},
"resource_uri": {
"type": "string"
}
},
"required": [
"executable",
"owner_server",
"slug",
"kind",
"label",
"title",
"description",
"inputs",
"outputs",
"assumptions",
"version",
"updated",
"canonical_url",
"api_url",
"resource_uri"
],
"additionalProperties": false
},
{
"type": "object",
"properties": {
"executable": {
"type": "boolean",
"const": false
},
"owner_server": {
"type": "string",
"description": "Host that serves this unit."
},
"slug": {
"type": "string"
},
"category": {
"type": "string",
"description": "benchmarks, simulators, experiments, games…"
},
"status": {
"type": "string"
},
"title": {
"type": "string"
},
"summary": {
"type": "string"
},
"canonical_url": {
"type": "string",
"description": "Cite this URL."
},
"resource_uri": {
"type": "string"
}
},
"required": [
"executable",
"owner_server",
"slug",
"category",
"status",
"title",
"canonical_url",
"resource_uri"
],
"additionalProperties": false
}
]
}
}
},
"required": [
"count",
"results"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false
}🟢get_lab(slug)
Get one Lab by slug, including formulas, assumptions, related SANTISMM content and its executable endpoint when one exists. Use this after list_labs or search_all; use the named calculate_* tool rather than reimplementing a published formula.
入力スキーマ
{
"type": "object",
"properties": {
"slug": {
"type": "string",
"minLength": 1,
"maxLength": 128,
"description": "Lab slug, e.g. 'evaluation-sample-size'."
}
},
"required": [
"slug"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}出力スキーマ
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"oneOf": [
{
"type": "object",
"properties": {
"executable": {
"type": "boolean",
"const": true
},
"owner_server": {
"type": "string",
"description": "Host that serves and versions this unit."
},
"slug": {
"type": "string"
},
"kind": {
"type": "string",
"enum": [
"calculator",
"converter",
"experiment",
"educational-game"
]
},
"label": {
"type": "string"
},
"title": {
"type": "string"
},
"description": {
"type": "string"
},
"inputs": {
"type": "array",
"items": {
"type": "string"
}
},
"outputs": {
"type": "array",
"items": {
"type": "string"
}
},
"formulas": {
"type": "array",
"items": {
"type": "string"
}
},
"assumptions": {
"type": "array",
"items": {
"type": "string"
}
},
"version": {
"type": "string"
},
"updated": {
"type": "string"
},
"canonical_url": {
"type": "string",
"description": "Cite this URL."
},
"api_url": {
"type": "string"
},
"calculation_url": {
"type": "string"
},
"related_content": {
"type": "array",
"items": {
"type": "object",
"properties": {
"title": {
"type": "string"
},
"url": {
"type": "string"
},
"relationship": {
"type": "string"
}
},
"required": [
"title",
"url",
"relationship"
],
"additionalProperties": false
}
},
"resource_uri": {
"type": "string"
}
},
"required": [
"executable",
"owner_server",
"slug",
"kind",
"label",
"title",
"description",
"inputs",
"outputs",
"assumptions",
"version",
"updated",
"canonical_url",
"api_url",
"resource_uri"
],
"additionalProperties": false
},
{
"type": "object",
"properties": {
"executable": {
"type": "boolean",
"const": false
},
"owner_server": {
"type": "string",
"description": "Host that serves this unit."
},
"slug": {
"type": "string"
},
"category": {
"type": "string",
"description": "benchmarks, simulators, experiments, games…"
},
"status": {
"type": "string"
},
"title": {
"type": "string"
},
"summary": {
"type": "string"
},
"canonical_url": {
"type": "string",
"description": "Cite this URL."
},
"resource_uri": {
"type": "string"
}
},
"required": [
"executable",
"owner_server",
"slug",
"category",
"status",
"title",
"canonical_url",
"resource_uri"
],
"additionalProperties": false
}
]
}🟢calculate_agent_economics(monthlyVolume, manualMinutes, hourlyCost, inputTokens, outputTokens, ...)
Calculate monthly operating cost, cost per verified outcome, manual baseline, savings, ROI and break-even success rate from explicit assumptions. Use this for an agent business case or scenario comparison; keep every monetary input in the same currency and cite the returned canonical_url.
入力スキーマ
{
"type": "object",
"properties": {
"monthlyVolume": {
"type": "number",
"minimum": 0,
"maximum": 1000000000,
"description": "Cases attempted per month."
},
"manualMinutes": {
"type": "number",
"minimum": 0,
"maximum": 10080,
"description": "Manual handling time per case."
},
"hourlyCost": {
"type": "number",
"minimum": 0,
"maximum": 1000000,
"description": "Fully loaded human hourly cost, in the chosen currency."
},
"inputTokens": {
"type": "number",
"minimum": 0,
"maximum": 100000000,
"description": "Input tokens per agent attempt."
},
"outputTokens": {
"type": "number",
"minimum": 0,
"maximum": 100000000,
"description": "Output tokens per agent attempt."
},
"inputPrice": {
"type": "number",
"minimum": 0,
"maximum": 1000000,
"description": "Model input price per million tokens, in the chosen currency."
},
"outputPrice": {
"type": "number",
"minimum": 0,
"maximum": 1000000,
"description": "Model output price per million tokens, in the chosen currency."
},
"toolCost": {
"type": "number",
"minimum": 0,
"maximum": 1000000,
"description": "External tool cost per attempt."
},
"retryRate": {
"type": "number",
"minimum": 0,
"maximum": 500,
"description": "Extra attempts as a percentage of initial volume."
},
"successRate": {
"type": "number",
"minimum": 1,
"maximum": 100,
"description": "Correctly verified outcomes as a percentage of cases."
},
"reviewRate": {
"type": "number",
"minimum": 0,
"maximum": 100,
"description": "Share of cases reviewed by a person."
},
"reviewMinutes": {
"type": "number",
"minimum": 0,
"maximum": 10080,
"description": "Human review minutes per reviewed case."
},
"reworkMinutes": {
"type": "number",
"minimum": 0,
"maximum": 10080,
"description": "Human rework minutes per failed case."
},
"locale": {
"description": "Language for interpretations, assumptions, formulas and warnings. The Labs execution service currently resolves fr/de/ja/zh to English and reports that fallback.",
"type": "string",
"enum": [
"en",
"es",
"pt",
"fr",
"de",
"ja",
"zh"
]
}
},
"required": [
"monthlyVolume",
"manualMinutes",
"hourlyCost",
"inputTokens",
"outputTokens",
"inputPrice",
"outputPrice",
"toolCost",
"retryRate",
"successRate",
"reviewRate",
"reviewMinutes",
"reworkMinutes"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}出力スキーマ
{
"type": "object",
"properties": {
"schema_version": {
"type": "string"
},
"source": {
"type": "string"
},
"language": {
"type": "string"
},
"requested_locale": {
"type": "string"
},
"resolved_locale": {
"type": "string"
},
"fallback": {
"type": "boolean"
},
"slug": {
"type": "string"
},
"version": {
"type": "string"
},
"updated": {
"type": "string"
},
"canonical_url": {
"type": "string",
"description": "Cite this URL."
},
"api_url": {
"type": "string"
},
"methodology_url": {
"type": "string"
},
"inputs": {
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {
"type": "number"
}
},
"units": {
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {
"type": "string"
}
},
"interpretation": {
"type": "string"
},
"assumptions": {
"type": "array",
"items": {
"type": "string"
}
},
"formulas": {
"type": "array",
"items": {
"type": "string"
}
},
"warnings": {
"type": "array",
"items": {
"type": "string"
}
},
"license": {
"type": "object",
"properties": {
"name": {
"type": "string"
},
"spdx": {
"type": "string"
},
"url": {
"type": "string"
}
},
"required": [
"name",
"spdx",
"url"
],
"additionalProperties": false
},
"results": {
"type": "object",
"properties": {
"attempts": {
"type": "number"
},
"executionCost": {
"type": "number"
},
"reviewCost": {
"type": "number"
},
"failedCases": {
"type": "number"
},
"reworkCost": {
"type": "number"
},
"operatingCost": {
"type": "number"
},
"manualCost": {
"type": "number"
},
"savings": {
"type": "number"
},
"roi": {
"type": "number"
},
"successfulOutcomes": {
"type": "number"
},
"costPerSuccess": {
"type": "number"
},
"costPerResolved": {
"type": "number"
},
"breakEvenSuccess": {
"type": "number"
},
"verdict": {
"type": "object",
"properties": {
"tone": {
"type": "string",
"enum": [
"positive",
"watch",
"negative"
]
},
"title": {
"type": "string"
},
"body": {
"type": "string"
}
},
"required": [
"tone",
"title",
"body"
],
"additionalProperties": false
}
},
"required": [
"attempts",
"executionCost",
"reviewCost",
"failedCases",
"reworkCost",
"operatingCost",
"manualCost",
"savings",
"roi",
"successfulOutcomes",
"costPerSuccess",
"costPerResolved",
"breakEvenSuccess",
"verdict"
],
"additionalProperties": false
}
},
"required": [
"schema_version",
"source",
"language",
"requested_locale",
"resolved_locale",
"fallback",
"slug",
"version",
"updated",
"canonical_url",
"api_url",
"methodology_url",
"inputs",
"units",
"interpretation",
"assumptions",
"formulas",
"warnings",
"license",
"results"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false
}🟢calculate_evaluation_sample_size(failureRate, confidence, margin, population, locale)
Calculate two different samples: how many independent evaluations are needed to detect at least one failure, and how many are needed to estimate its rate at a chosen margin. Use this when a user asks how many tests are enough; do not interpret zero observed failures as proof of zero risk.
入力スキーマ
{
"type": "object",
"properties": {
"failureRate": {
"type": "number",
"minimum": 0.0001,
"maximum": 99.9999,
"description": "Failure rate to detect, in percent."
},
"confidence": {
"anyOf": [
{
"type": "number",
"const": 90
},
{
"type": "number",
"const": 95
},
{
"type": "number",
"const": 99
}
],
"description": "Confidence level, in percent."
},
"margin": {
"type": "number",
"minimum": 0.1,
"maximum": 50,
"description": "Margin for estimating the failure rate, in percentage points."
},
"population": {
"type": "number",
"minimum": 1,
"maximum": 1000000000,
"description": "Number of distinct evaluable cases."
},
"locale": {
"description": "Language for interpretations, assumptions, formulas and warnings. The Labs execution service currently resolves fr/de/ja/zh to English and reports that fallback.",
"type": "string",
"enum": [
"en",
"es",
"pt",
"fr",
"de",
"ja",
"zh"
]
}
},
"required": [
"failureRate",
"confidence",
"margin",
"population"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}出力スキーマ
{
"type": "object",
"properties": {
"schema_version": {
"type": "string"
},
"source": {
"type": "string"
},
"language": {
"type": "string"
},
"requested_locale": {
"type": "string"
},
"resolved_locale": {
"type": "string"
},
"fallback": {
"type": "boolean"
},
"slug": {
"type": "string"
},
"version": {
"type": "string"
},
"updated": {
"type": "string"
},
"canonical_url": {
"type": "string",
"description": "Cite this URL."
},
"api_url": {
"type": "string"
},
"methodology_url": {
"type": "string"
},
"inputs": {
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {
"type": "number"
}
},
"units": {
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {
"type": "string"
}
},
"interpretation": {
"type": "string"
},
"assumptions": {
"type": "array",
"items": {
"type": "string"
}
},
"formulas": {
"type": "array",
"items": {
"type": "string"
}
},
"warnings": {
"type": "array",
"items": {
"type": "string"
}
},
"license": {
"type": "object",
"properties": {
"name": {
"type": "string"
},
"spdx": {
"type": "string"
},
"url": {
"type": "string"
}
},
"required": [
"name",
"spdx",
"url"
],
"additionalProperties": false
},
"results": {
"type": "object",
"properties": {
"detect": {
"type": "number"
},
"estimate": {
"type": "number"
},
"expected": {
"type": "number"
},
"zero": {
"type": "number"
}
},
"required": [
"detect",
"estimate",
"expected",
"zero"
],
"additionalProperties": false
}
},
"required": [
"schema_version",
"source",
"language",
"requested_locale",
"resolved_locale",
"fallback",
"slug",
"version",
"updated",
"canonical_url",
"api_url",
"methodology_url",
"inputs",
"units",
"interpretation",
"assumptions",
"formulas",
"warnings",
"license",
"results"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false
}🟢calculate_human_supervision_capacity(volume, sample, reviewMinutes, escalationRate, escalationMinutes, ...)
Calculate review and escalation workload, required FTE, available headroom or backlog, monthly labour cost and sustainable case volume. Use this before production rollout to test whether the stated human-oversight model is operationally credible; the result uses averages and is not a queueing simulation.
入力スキーマ
{
"type": "object",
"properties": {
"volume": {
"type": "number",
"minimum": 0,
"maximum": 1000000000,
"description": "Agent cases per month."
},
"sample": {
"type": "number",
"minimum": 0,
"maximum": 100,
"description": "Share of all cases selected for routine review, in percent."
},
"reviewMinutes": {
"type": "number",
"minimum": 0,
"maximum": 10080,
"description": "Minutes per routine review."
},
"escalationRate": {
"type": "number",
"minimum": 0,
"maximum": 100,
"description": "Share of cases escalated, in percent."
},
"escalationMinutes": {
"type": "number",
"minimum": 0,
"maximum": 10080,
"description": "Minutes per escalation."
},
"workdays": {
"type": "number",
"minimum": 1,
"maximum": 31,
"description": "Working days per month."
},
"hoursDay": {
"type": "number",
"minimum": 0.1,
"maximum": 24,
"description": "Paid hours per working day."
},
"utilization": {
"type": "number",
"minimum": 1,
"maximum": 100,
"description": "Share of paid time available for review and escalation, in percent."
},
"reviewers": {
"type": "number",
"minimum": 0.1,
"maximum": 1000000,
"description": "Available reviewer FTE."
},
"hourlyCost": {
"type": "number",
"minimum": 0,
"maximum": 1000000,
"description": "Fully loaded reviewer hourly cost, in the chosen currency."
},
"locale": {
"description": "Language for interpretations, assumptions, formulas and warnings. The Labs execution service currently resolves fr/de/ja/zh to English and reports that fallback.",
"type": "string",
"enum": [
"en",
"es",
"pt",
"fr",
"de",
"ja",
"zh"
]
}
},
"required": [
"volume",
"sample",
"reviewMinutes",
"escalationRate",
"escalationMinutes",
"workdays",
"hoursDay",
"utilization",
"reviewers",
"hourlyCost"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}出力スキーマ
{
"type": "object",
"properties": {
"schema_version": {
"type": "string"
},
"source": {
"type": "string"
},
"language": {
"type": "string"
},
"requested_locale": {
"type": "string"
},
"resolved_locale": {
"type": "string"
},
"fallback": {
"type": "boolean"
},
"slug": {
"type": "string"
},
"version": {
"type": "string"
},
"updated": {
"type": "string"
},
"canonical_url": {
"type": "string",
"description": "Cite this URL."
},
"api_url": {
"type": "string"
},
"methodology_url": {
"type": "string"
},
"inputs": {
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {
"type": "number"
}
},
"units": {
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {
"type": "string"
}
},
"interpretation": {
"type": "string"
},
"assumptions": {
"type": "array",
"items": {
"type": "string"
}
},
"formulas": {
"type": "array",
"items": {
"type": "string"
}
},
"warnings": {
"type": "array",
"items": {
"type": "string"
}
},
"license": {
"type": "object",
"properties": {
"name": {
"type": "string"
},
"spdx": {
"type": "string"
},
"url": {
"type": "string"
}
},
"required": [
"name",
"spdx",
"url"
],
"additionalProperties": false
},
"results": {
"type": "object",
"properties": {
"routine": {
"type": "number"
},
"escalations": {
"type": "number"
},
"workload": {
"type": "number"
},
"productivePerFte": {
"type": "number"
},
"requiredFte": {
"type": "number"
},
"headroom": {
"type": "number"
},
"cost": {
"type": "number"
},
"backlogDays": {
"type": "number"
},
"sustainableVolume": {
"type": "number"
}
},
"required": [
"routine",
"escalations",
"workload",
"productivePerFte",
"requiredFte",
"headroom",
"cost",
"backlogDays",
"sustainableVolume"
],
"additionalProperties": false
}
},
"required": [
"schema_version",
"source",
"language",
"requested_locale",
"resolved_locale",
"fallback",
"slug",
"version",
"updated",
"canonical_url",
"api_url",
"methodology_url",
"inputs",
"units",
"interpretation",
"assumptions",
"formulas",
"warnings",
"license",
"results"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false
}🟢get_related(domain, slug, locale)
Traverse the knowledge graph: given a unit, return its neighbours — the units it links to (outgoing) and the units that reference it (incoming), each with the relationship type. Use this after a `get_*` call to widen an answer with adjacent units.
入力スキーマ
{
"type": "object",
"properties": {
"domain": {
"type": "string",
"enum": [
"knowledge",
"patterns",
"architectures",
"governance",
"handbook"
],
"description": "Core knowledge domain containing the starting unit."
},
"slug": {
"type": "string",
"description": "Slug of the unit to start from (or an HRN id when domain is 'handbook')."
},
"locale": {
"description": "Language of the returned body. Default: en.",
"type": "string",
"enum": [
"en",
"es",
"pt",
"fr",
"de",
"ja",
"zh"
]
}
},
"required": [
"domain",
"slug"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}出力スキーマ
{
"type": "object",
"properties": {
"unit": {
"type": "object",
"properties": {
"domain": {
"type": "string"
},
"id": {
"type": "string"
},
"slug": {
"type": "string"
},
"category": {
"type": "string"
},
"name": {
"type": "string"
},
"summary": {
"type": "string"
},
"status": {
"type": "string"
},
"evidence": {
"description": "Evidence-First provenance: weight claims by this.",
"type": "object",
"properties": {
"evidenceLevel": {
"type": "string"
},
"confidenceLevel": {
"type": "string"
},
"sourceType": {
"type": "array",
"items": {
"type": "string"
}
}
},
"additionalProperties": false
},
"updated": {
"type": "string"
},
"locale": {
"type": "string"
},
"canonical_url": {
"description": "Cite this URL.",
"type": "string"
},
"api_url": {
"type": "string"
},
"resource_uri": {
"description": "Read this card as an MCP Resource.",
"type": "string"
}
},
"required": [
"domain",
"slug",
"name"
],
"additionalProperties": {}
},
"outgoing": {
"type": "array",
"items": {
"type": "object",
"properties": {
"domain": {
"type": "string"
},
"id": {
"type": "string"
},
"slug": {
"type": "string"
},
"category": {
"type": "string"
},
"name": {
"type": "string"
},
"summary": {
"type": "string"
},
"status": {
"type": "string"
},
"evidence": {
"description": "Evidence-First provenance: weight claims by this.",
"type": "object",
"properties": {
"evidenceLevel": {
"type": "string"
},
"confidenceLevel": {
"type": "string"
},
"sourceType": {
"type": "array",
"items": {
"type": "string"
}
}
},
"additionalProperties": false
},
"updated": {
"type": "string"
},
"locale": {
"type": "string"
},
"canonical_url": {
"description": "Cite this URL.",
"type": "string"
},
"api_url": {
"type": "string"
},
"resource_uri": {
"description": "Read this card as an MCP Resource.",
"type": "string"
},
"type": {
"type": "string"
}
},
"required": [
"domain",
"slug",
"name",
"type"
],
"additionalProperties": {}
}
},
"incoming": {
"type": "array",
"items": {
"type": "object",
"properties": {
"domain": {
"type": "string"
},
"id": {
"type": "string"
},
"slug": {
"type": "string"
},
"category": {
"type": "string"
},
"name": {
"type": "string"
},
"summary": {
"type": "string"
},
"status": {
"type": "string"
},
"evidence": {
"description": "Evidence-First provenance: weight claims by this.",
"type": "object",
"properties": {
"evidenceLevel": {
"type": "string"
},
"confidenceLevel": {
"type": "string"
},
"sourceType": {
"type": "array",
"items": {
"type": "string"
}
}
},
"additionalProperties": false
},
"updated": {
"type": "string"
},
"locale": {
"type": "string"
},
"canonical_url": {
"description": "Cite this URL.",
"type": "string"
},
"api_url": {
"type": "string"
},
"resource_uri": {
"description": "Read this card as an MCP Resource.",
"type": "string"
},
"type": {
"type": "string"
}
},
"required": [
"domain",
"slug",
"name",
"type"
],
"additionalProperties": {}
}
}
},
"required": [
"unit",
"outgoing",
"incoming"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false
}🟢list_homeric_places(locale)
List every place in the Homeric Atlas with its identification class, its confidence score and how many competing identifications it carries. Use this to browse the atlas; use `get_homeric_place` once you have a slug. Identification classes: accepted (an excavated site with consensus), plausible (a real place, contested), speculative (a minority reading or a later tradition), mythical (the poem places it outside the mappable world). Confidence is a published 0-12 rubric - textual, archaeological, scholarly and geographic, 0-3 each - and is an editorial judgement, not a probability.
入力スキーマ
{
"type": "object",
"properties": {
"locale": {
"description": "Language of the returned body. Default: en.",
"type": "string",
"enum": [
"en",
"es",
"pt",
"fr",
"de",
"ja",
"zh"
]
}
},
"$schema": "https://json-schema.org/draft/2020-12/schema"
}出力スキーマ
{
"type": "object",
"properties": {
"count": {
"type": "number"
},
"results": {
"type": "array",
"items": {
"type": "object",
"properties": {
"kind": {
"type": "string"
},
"id": {
"type": "string"
},
"slug": {
"type": "string"
},
"name": {
"type": "string"
},
"summary": {
"type": "string"
},
"identification": {
"type": "string"
},
"region": {
"type": "string"
},
"work": {
"type": "string"
},
"citation": {
"type": "string"
},
"unlocated": {
"type": "boolean"
},
"hypotheses": {
"type": "number"
},
"confidence": {
"anyOf": [
{
"type": "object",
"properties": {
"textual": {
"type": "number"
},
"archaeological": {
"type": "number"
},
"scholarly": {
"type": "number"
},
"geographic": {
"type": "number"
},
"score": {
"type": "number"
},
"band": {
"type": "string"
}
},
"additionalProperties": {}
},
{
"type": "null"
}
]
},
"canonical_url": {
"description": "Cite this URL.",
"type": "string"
},
"api_url": {
"type": "string"
}
},
"required": [
"kind",
"slug",
"name"
],
"additionalProperties": {}
}
}
},
"required": [
"count",
"results"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false
}🟢get_homeric_place(slug, locale)
Get one place by slug: every identification proposed for it, each with its own coordinates, class, 0-12 rubric and sources, plus the attested passages. Use this when you need to weigh the evidence for a location, or to cite it; a place the poem does not locate carries no coordinates at all.
入力スキーマ
{
"type": "object",
"properties": {
"slug": {
"type": "string",
"description": "Place slug, e.g. 'ithaca'."
},
"locale": {
"description": "Language of the returned body. Default: en.",
"type": "string",
"enum": [
"en",
"es",
"pt",
"fr",
"de",
"ja",
"zh"
]
}
},
"required": [
"slug"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}出力スキーマ
{
"type": "object",
"properties": {},
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": {}
}🟢list_homeric_episodes(locale)
List every episode of the Iliad and the Odyssey held in the atlas, in reading order, with its passage, the places it involves and how firmly it can be located. Use this to find the episode you want; use `get_homeric_episode` for its theories and sources.
入力スキーマ
{
"type": "object",
"properties": {
"locale": {
"description": "Language of the returned body. Default: en.",
"type": "string",
"enum": [
"en",
"es",
"pt",
"fr",
"de",
"ja",
"zh"
]
}
},
"$schema": "https://json-schema.org/draft/2020-12/schema"
}出力スキーマ
{
"type": "object",
"properties": {
"count": {
"type": "number"
},
"results": {
"type": "array",
"items": {
"type": "object",
"properties": {
"kind": {
"type": "string"
},
"id": {
"type": "string"
},
"slug": {
"type": "string"
},
"name": {
"type": "string"
},
"summary": {
"type": "string"
},
"identification": {
"type": "string"
},
"region": {
"type": "string"
},
"work": {
"type": "string"
},
"citation": {
"type": "string"
},
"unlocated": {
"type": "boolean"
},
"hypotheses": {
"type": "number"
},
"confidence": {
"anyOf": [
{
"type": "object",
"properties": {
"textual": {
"type": "number"
},
"archaeological": {
"type": "number"
},
"scholarly": {
"type": "number"
},
"geographic": {
"type": "number"
},
"score": {
"type": "number"
},
"band": {
"type": "string"
}
},
"additionalProperties": {}
},
{
"type": "null"
}
]
},
"canonical_url": {
"description": "Cite this URL.",
"type": "string"
},
"api_url": {
"type": "string"
}
},
"required": [
"kind",
"slug",
"name"
],
"additionalProperties": {}
}
}
},
"required": [
"count",
"results"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false
}🟢get_homeric_episode(slug, locale)
Get one episode by slug: the passage, the narrative, the competing theories about where it happened (each with its proponent and sources), the confidence rubric and the FAQs. Use this when the question is where an episode took place and who argued for it.
入力スキーマ
{
"type": "object",
"properties": {
"slug": {
"type": "string",
"description": "Episode slug, e.g. 'nekyia'."
},
"locale": {
"description": "Language of the returned body. Default: en.",
"type": "string",
"enum": [
"en",
"es",
"pt",
"fr",
"de",
"ja",
"zh"
]
}
},
"required": [
"slug"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}出力スキーマ
{
"type": "object",
"properties": {},
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": {}
}🟢list_homeric_routes(locale)
List the reconstructed itineraries (the nostos of Odysseus and the others), each with its rival reconstructions scored separately. Use this to see which voyages the atlas reconstructs before fetching one.
入力スキーマ
{
"type": "object",
"properties": {
"locale": {
"description": "Language of the returned body. Default: en.",
"type": "string",
"enum": [
"en",
"es",
"pt",
"fr",
"de",
"ja",
"zh"
]
}
},
"$schema": "https://json-schema.org/draft/2020-12/schema"
}出力スキーマ
{
"type": "object",
"properties": {
"count": {
"type": "number"
},
"results": {
"type": "array",
"items": {
"type": "object",
"properties": {
"kind": {
"type": "string"
},
"id": {
"type": "string"
},
"slug": {
"type": "string"
},
"name": {
"type": "string"
},
"summary": {
"type": "string"
},
"identification": {
"type": "string"
},
"region": {
"type": "string"
},
"work": {
"type": "string"
},
"citation": {
"type": "string"
},
"unlocated": {
"type": "boolean"
},
"hypotheses": {
"type": "number"
},
"confidence": {
"anyOf": [
{
"type": "object",
"properties": {
"textual": {
"type": "number"
},
"archaeological": {
"type": "number"
},
"scholarly": {
"type": "number"
},
"geographic": {
"type": "number"
},
"score": {
"type": "number"
},
"band": {
"type": "string"
}
},
"additionalProperties": {}
},
{
"type": "null"
}
]
},
"canonical_url": {
"description": "Cite this URL.",
"type": "string"
},
"api_url": {
"type": "string"
}
},
"required": [
"kind",
"slug",
"name"
],
"additionalProperties": {}
}
}
},
"required": [
"count",
"results"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false
}🟢get_homeric_route(slug, locale)
Get one route by slug: each reconstruction variant with its ordered stops, the hypothesis chosen at each stop, its confidence rubric and its sources. Use this to compare rival reconstructions of a voyage: they are returned side by side rather than merged.
入力スキーマ
{
"type": "object",
"properties": {
"slug": {
"type": "string",
"description": "Route slug, e.g. 'odysseus-nostos'."
},
"locale": {
"description": "Language of the returned body. Default: en.",
"type": "string",
"enum": [
"en",
"es",
"pt",
"fr",
"de",
"ja",
"zh"
]
}
},
"required": [
"slug"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}出力スキーマ
{
"type": "object",
"properties": {},
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": {}
}🟢list_claims(claim_type, locale)
List the load-bearing claims of the corpus, each tagged as observed_fact, industry_synthesis, santismm_thesis or strategic_hypothesis, with its confidence and the units it underpins. Use this before quoting the handbook to know whether a statement is evidence, a reading of the industry, or a position taken. Filter by `claim_type` to get only what is checkable.
入力スキーマ
{
"type": "object",
"properties": {
"claim_type": {
"description": "Restrict to one rung of the ladder. Omit for all.",
"type": "string",
"enum": [
"observed_fact",
"industry_synthesis",
"santismm_thesis",
"strategic_hypothesis"
]
},
"locale": {
"description": "Language of the returned body. Default: en.",
"type": "string",
"enum": [
"en",
"es",
"pt",
"fr",
"de",
"ja",
"zh"
]
}
},
"$schema": "https://json-schema.org/draft/2020-12/schema"
}出力スキーマ
{
"type": "object",
"properties": {
"count": {
"type": "number"
},
"results": {
"type": "array",
"items": {
"type": "object",
"properties": {
"type": {
"type": "string",
"const": "claim"
},
"id": {
"type": "string"
},
"slug": {
"type": "string"
},
"claim_type": {
"type": "string",
"enum": [
"observed_fact",
"industry_synthesis",
"santismm_thesis",
"strategic_hypothesis"
]
},
"confidence_level": {
"type": "string"
},
"statement": {
"type": "string"
},
"supports": {
"type": "array",
"items": {
"type": "string"
}
},
"reviewed": {
"type": "string"
},
"resource_uri": {
"type": "string"
}
},
"required": [
"type",
"id",
"slug",
"claim_type",
"confidence_level",
"supports",
"reviewed",
"resource_uri"
],
"additionalProperties": false
}
}
},
"required": [
"count",
"results"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false
}🟢get_claim(id, locale)
Get one claim by id (HE-CLAIM-001) or slug: the statement, what it rests on, its structured sources, and — always present — what it does NOT establish and the observation that would retire it. Use this to cite the corpus honestly, or to check whether a result you have just measured confirms or falsifies a claim it makes.
入力スキーマ
{
"type": "object",
"properties": {
"id": {
"type": "string",
"description": "Claim id (e.g. 'HE-CLAIM-001') or slug."
},
"locale": {
"description": "Language of the returned body. Default: en.",
"type": "string",
"enum": [
"en",
"es",
"pt",
"fr",
"de",
"ja",
"zh"
]
}
},
"required": [
"id"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}出力スキーマ
{
"type": "object",
"properties": {},
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": {}
}コミュニティ
エビデンス
最近の観測
検証済みバージョンは記録されていませんツール 30 件
検証済みバージョンは記録されていませんツール 30 件