corpus
Read-only MCP access to Vela's corpus of human experience: cited passages, coordinates, reading path
我该使用它吗
质量与安全性
B
发现（9）
- LOWTool 'vela.corpus.query' doesn't follow camelCase/snake_case在 vela.corpus.query 中
- LOWTool 'vela.corpus.list_topics' doesn't follow camelCase/snake_case在 vela.corpus.list_topics 中
- LOWTool 'vela.corpus.describe_topic' doesn't follow camelCase/snake_case在 vela.corpus.describe_topic 中
- LOWTool 'vela.corpus.ground_claim' doesn't follow camelCase/snake_case在 vela.corpus.ground_claim 中
- LOWTool 'vela.corpus.witness' doesn't follow camelCase/snake_case在 vela.corpus.witness 中
- LOWTool 'vela.magazine.sequence_path' doesn't follow camelCase/snake_case在 vela.magazine.sequence_path 中
- LOWTool 'vela.magazine.relation_floor' doesn't follow camelCase/snake_case在 vela.magazine.relation_floor 中
- LOWTool 'vela.research.list_studies' doesn't follow camelCase/snake_case在 vela.research.list_studies 中
- LOWTool 'vela.research.get_study' doesn't follow camelCase/snake_case在 vela.research.get_study 中
基于对工具定义和协议合规性的自动分析。
上下文开销
~4,383token 数（工具定义）
~4.5 KB典型响应大小
对注意力有显著影响（占 128k 上下文窗口的 3.42%）
这是每次将服务器的工具加载到模型上下文窗口时所消耗的大致 token 数。数值越高，可用于其他任务的注意力就越少。
安装
一键安装
将以下内容添加到你的 `claude_desktop_config.json` 文件中：
{
"mcpServers": {
"corpus": {
"url": "https://vela.study/mcp"
}
}
}远程端点
https://vela.study/mcpstreamable-http它能做什么
工具清单
工具（9）
🟢 只读🟡 写入🔴 删除⚪ 未知
🟢vela.corpus.query(topic, axes, themes, qualities, genre, ...)
Ask the corpus by COORDINATE rather than keyword. Filter works by axis weights (e.g. religion ∈ {T,s} AND work ∈ {T,s} returns the God-and-Work source set across genres), controlled themes, qualities/emotions, genre, and free text. Returns card metadata: the one-line claim, themes, coordinates, qualities. FREE and read-only. [capability: library-extraction-cards · mirrors: POST /api/corpus/query]
输入模式
{
"type": "object",
"properties": {
"topic": {
"default": "being-human",
"description": "Coordinate system to query (topic_configs.slug).",
"type": "string"
},
"axes": {
"description": "Axis → allowed weights. ALL listed axes must match. e.g. {\"religion\":[\"T\",\"s\"],\"work\":[\"T\",\"s\"]}",
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {
"type": "array",
"items": {
"type": "string"
}
}
},
"themes": {
"description": "Cards citing ANY of these controlled themes.",
"type": "array",
"items": {
"type": "string"
}
},
"qualities": {
"description": "Cards carrying ANY of these qualities (emotions, for being-human).",
"type": "array",
"items": {
"type": "string"
}
},
"genre": {
"type": "string"
},
"text": {
"description": "Substring match over title / author / one-line claim.",
"type": "string"
},
"include_passages": {
"default": false,
"description": "Include theme-anchored passage pointers.",
"type": "boolean"
},
"limit": {
"default": 50,
"type": "integer",
"minimum": 1,
"maximum": 200
},
"offset": {
"default": 0,
"type": "integer",
"minimum": 0,
"maximum": 9007199254740991
}
},
"$schema": "http://json-schema.org/draft-07/schema#"
}输出模式
{
"type": "object",
"properties": {
"topic": {
"type": "string"
},
"total": {
"type": "number"
},
"returned": {
"type": "number"
},
"hits": {
"type": "array",
"items": {
"type": "object",
"properties": {
"sourceSlug": {
"type": "string"
},
"libraryId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
]
},
"title": {
"type": "string"
},
"author": {
"type": "string"
},
"year": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
]
},
"genre": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
]
},
"oneLineClaim": {
"type": "string"
},
"themes": {
"type": "array",
"items": {
"type": "string"
}
},
"coordinates": {
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {
"type": "string"
}
},
"qualities": {
"type": "array",
"items": {
"type": "string"
}
},
"signaturePassages": {
"type": "array",
"items": {
"type": "object",
"properties": {
"code": {
"type": "string"
},
"theme": {
"type": "string"
},
"quote": {
"type": "string"
}
},
"required": [
"code",
"theme",
"quote"
],
"additionalProperties": false
}
}
},
"required": [
"sourceSlug",
"libraryId",
"title",
"author",
"year",
"genre",
"oneLineClaim",
"themes",
"coordinates",
"qualities"
],
"additionalProperties": {}
}
},
"truncated": {
"type": "boolean"
},
"applied": {
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {}
}
},
"required": [
"topic",
"total",
"returned",
"hits",
"applied"
],
"$schema": "http://json-schema.org/draft-07/schema#",
"additionalProperties": false
}🟢vela.corpus.list_topics
List the coordinate systems the corpus can be queried through — each with its thesis, axes, and controlled vocabularies. Call this before vela.corpus.query to learn what axes and themes exist. FREE and read-only. [capability: topic-coordinate-systems · mirrors: GET /api/corpus/topics]
输入模式
{
"type": "object",
"properties": {},
"$schema": "http://json-schema.org/draft-07/schema#"
}输出模式
{
"type": "object",
"properties": {
"topics": {
"type": "array",
"items": {
"type": "object",
"properties": {
"slug": {
"type": "string"
},
"name": {
"type": "string"
},
"thesis": {
"type": "string"
},
"axes": {
"type": "array",
"items": {
"type": "object",
"properties": {
"key": {
"type": "string"
},
"label": {
"type": "string"
},
"description": {
"type": "string"
}
},
"required": [
"key",
"label"
],
"additionalProperties": {}
}
},
"axisWeights": {
"type": "array",
"items": {
"type": "string"
}
},
"themeCount": {
"type": "number"
},
"qualityCount": {
"type": "number"
}
},
"required": [
"slug",
"name",
"axes",
"axisWeights",
"themeCount",
"qualityCount"
],
"additionalProperties": false
}
}
},
"required": [
"topics"
],
"$schema": "http://json-schema.org/draft-07/schema#",
"additionalProperties": false
}🟢vela.corpus.describe_topic(topic)
Describe ONE topic in full — its axes and their operative definitions, its complete controlled theme and quality vocabularies, plus the vocabulary actually IN USE across the corpus with counts. The declared vocabulary and the used vocabulary are different facts; this returns both. FREE and read-only. [capability: topic-coordinate-systems · mirrors: GET /api/corpus/topics/:slug]
输入模式
{
"type": "object",
"properties": {
"topic": {
"default": "being-human",
"type": "string"
}
},
"$schema": "http://json-schema.org/draft-07/schema#"
}输出模式
{
"type": "object",
"properties": {
"declared": {
"type": "object",
"properties": {
"slug": {
"type": "string"
},
"name": {
"type": "string"
},
"thesis": {
"type": "string"
},
"axes": {
"type": "array",
"items": {}
},
"themes": {
"type": "array",
"items": {}
},
"qualities": {
"type": "array",
"items": {}
},
"axisWeights": {
"type": "array",
"items": {
"type": "string"
}
}
},
"required": [
"slug",
"name",
"axes",
"themes",
"qualities"
],
"additionalProperties": {}
},
"inUse": {
"type": "object",
"properties": {
"cards": {
"type": "number"
},
"themes": {
"type": "array",
"items": {
"type": "object",
"properties": {
"slug": {
"type": "string"
},
"count": {
"type": "number"
}
},
"required": [
"slug",
"count"
],
"additionalProperties": false
}
},
"qualities": {
"type": "array",
"items": {
"type": "object",
"properties": {
"slug": {
"type": "string"
},
"count": {
"type": "number"
}
},
"required": [
"slug",
"count"
],
"additionalProperties": false
}
},
"genres": {
"type": "array",
"items": {
"type": "object",
"properties": {
"slug": {
"type": "string"
},
"count": {
"type": "number"
}
},
"required": [
"slug",
"count"
],
"additionalProperties": false
}
},
"axes": {
"type": "array",
"items": {
"type": "object",
"properties": {
"key": {
"type": "string"
},
"weights": {
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {
"type": "number"
}
}
},
"required": [
"key",
"weights"
],
"additionalProperties": false
}
}
},
"required": [
"cards",
"themes",
"qualities",
"genres",
"axes"
],
"additionalProperties": {}
}
},
"required": [
"declared",
"inUse"
],
"$schema": "http://json-schema.org/draft-07/schema#",
"additionalProperties": false
}🟢vela.corpus.ground_claim(claim, limit)
Ground a claim in the corpus: hybrid semantic + theme retrieval over real passages, returning citations with source, passage code, scores, and a SHORT snippet. Use to check whether the corpus supports, complicates or is silent on an assertion. COSTS a small amount (one embedding per call). [capability: corpus-ingestion-dual-grade · mirrors: internal — lib/audit/retrieve.ts]
输入模式
{
"type": "object",
"properties": {
"claim": {
"type": "string",
"minLength": 3,
"description": "The claim to ground."
},
"limit": {
"default": 8,
"type": "integer",
"minimum": 1,
"maximum": 20
}
},
"required": [
"claim"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}输出模式
{
"type": "object",
"properties": {
"claim": {
"type": "string"
},
"hits": {
"type": "array",
"items": {
"type": "object",
"properties": {
"passageCode": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
]
},
"sourceTitle": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
]
},
"themes": {
"type": "array",
"items": {
"type": "string"
}
},
"score": {
"type": "number"
},
"rationale": {
"type": "string"
},
"snippet": {
"type": "string"
},
"snippetTruncated": {
"type": "boolean"
}
},
"required": [
"passageCode",
"sourceTitle",
"themes",
"score",
"rationale",
"snippet",
"snippetTruncated"
],
"additionalProperties": false
}
}
},
"required": [
"claim",
"hits"
],
"$schema": "http://json-schema.org/draft-07/schema#",
"additionalProperties": false
}🟢vela.corpus.witness(themes, emotions, axes, problem_slug, condition_slug, ...)
Literary Witness Rail (ASN-1577): return passages and one-line claims from Vela's 762-work corpus that illuminate the given themes and/or emotions. Designed for frame-family profile pages — PersonFrame × ProblemFrame × ConditionFrame — to add an inside-out layer (what writers who lived this say) alongside the outside-in portrait the frame join produces. Results carry evidence_grade 'T1' (single-extractor) until PRN-282 lands. FREE for claims; costs one embedding for the passage path. [capability: literary-witness · mirrors: GET /api/vela/witness]
输入模式
{
"type": "object",
"properties": {
"themes": {
"description": "Controlled themes from Vela's vocabulary (e.g. 'fairness', 'recognition').",
"type": "array",
"items": {
"type": "string",
"minLength": 1
}
},
"emotions": {
"description": "Emotions to match (e.g. 'shame', 'betrayal', 'grief'). At least one of themes or emotions is required.",
"type": "array",
"items": {
"type": "string",
"minLength": 1
}
},
"axes": {
"description": "Axis weight filters for claims only — same format as vela.corpus.query (e.g. {work:[\"T\",\"s\"]}).",
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {
"type": "array",
"items": {
"type": "string"
}
}
},
"problem_slug": {
"description": "ProblemFrame entity slug (echoed in response; reserved for frame_tags[] pre-cache after PA-1153 ID-freeze).",
"type": "string"
},
"condition_slug": {
"description": "ConditionFrame entity slug (same reservation as problem_slug).",
"type": "string"
},
"max_passages": {
"default": 5,
"description": "Max passages to return (default 5).",
"type": "integer",
"minimum": 1,
"maximum": 10
},
"max_claims": {
"default": 3,
"description": "Max one-line claims to return (default 3).",
"type": "integer",
"minimum": 1,
"maximum": 8
}
},
"$schema": "http://json-schema.org/draft-07/schema#"
}输出模式
{
"type": "object",
"properties": {
"passages": {
"type": "array",
"items": {
"type": "object",
"properties": {
"passage_code": {
"type": "string"
},
"text": {
"type": "string"
},
"source_title": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
]
},
"author": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
]
},
"charge": {
"type": "number"
},
"themes": {
"type": "array",
"items": {
"type": "string"
}
},
"page_range": {
"type": "null"
}
},
"required": [
"passage_code",
"text",
"source_title",
"author",
"charge",
"themes",
"page_range"
],
"additionalProperties": false
}
},
"claims": {
"type": "array",
"items": {
"type": "object",
"properties": {
"claim": {
"type": "string"
},
"source_title": {
"type": "string"
},
"author": {
"type": "string"
},
"themes": {
"type": "array",
"items": {
"type": "string"
}
}
},
"required": [
"claim",
"source_title",
"author",
"themes"
],
"additionalProperties": false
}
},
"evidence_grade": {
"type": "string",
"const": "T1"
},
"query": {
"type": "object",
"properties": {
"themes": {
"type": "array",
"items": {
"type": "string"
}
},
"emotions": {
"type": "array",
"items": {
"type": "string"
}
},
"axes": {
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {
"type": "array",
"items": {
"type": "string"
}
}
},
"problem_slug": {
"type": "string"
},
"condition_slug": {
"type": "string"
}
},
"required": [
"themes",
"emotions"
],
"additionalProperties": {}
}
},
"required": [
"passages",
"claims",
"evidence_grade",
"query"
],
"$schema": "http://json-schema.org/draft-07/schema#",
"additionalProperties": false
}🟢vela.magazine.sequence_path(emotions, forms, property, limit)
Ask what this magazine would actually give a reader who said they wanted these things. Returns the REAL sequenced path with the rationale for each piece — the same core the anonymous intake calls, not a preview. Read-only: writes nothing and records no signal. [capability: adaptive-magazine-engine · mirrors: POST /api/magazine/start-path]
输入模式
{
"type": "object",
"properties": {
"emotions": {
"description": "Emotions the reader is steering by.",
"maxItems": 12,
"type": "array",
"items": {
"type": "string",
"minLength": 1,
"maxLength": 64
}
},
"forms": {
"description": "Article forms to steer by. At least one of emotions/forms is required.",
"maxItems": 12,
"type": "array",
"items": {
"type": "string",
"minLength": 1,
"maxLength": 64
}
},
"property": {
"description": "Property id; defaults to vela.",
"type": "string",
"minLength": 1,
"maxLength": 64
},
"limit": {
"description": "Pieces to return (default 4).",
"type": "integer",
"minimum": 1,
"maximum": 12
}
},
"$schema": "http://json-schema.org/draft-07/schema#"
}输出模式
{
"type": "object",
"properties": {
"property": {
"type": "string"
},
"path": {
"type": "array",
"items": {
"type": "object",
"properties": {
"id": {
"type": "string"
},
"slug": {
"type": "string"
},
"title": {
"type": "string"
},
"rationale": {
"type": "string"
},
"personalized": {
"type": "boolean"
}
},
"required": [
"id",
"slug",
"title",
"rationale",
"personalized"
],
"additionalProperties": false
}
}
},
"required": [
"property",
"path"
],
"$schema": "http://json-schema.org/draft-07/schema#",
"additionalProperties": false
}🟢vela.magazine.relation_floor(property)
Whether a magazine's corpus can support the adaptive promise its pages render. Reports, per property, each relational dimension's fill AND its separating power — a field present on every piece with one distinct value carries no information, so fill rate alone is misleading. Read-only. [capability: adaptive-magazine-engine · mirrors: npm run magazine:relation-floor]
输入模式
{
"type": "object",
"properties": {
"property": {
"description": "Restrict to one property id; omit for every property with published pieces.",
"type": "string",
"minLength": 1,
"maxLength": 64
}
},
"$schema": "http://json-schema.org/draft-07/schema#"
}输出模式
{
"type": "object",
"properties": {
"properties": {
"type": "array",
"items": {
"type": "object",
"properties": {
"property": {
"type": "string"
},
"published": {
"type": "number"
},
"dimensions": {
"type": "array",
"items": {
"type": "object",
"properties": {
"name": {
"type": "string"
},
"key": {
"type": "string"
},
"fill": {
"type": "number"
},
"distinct": {
"type": "number"
},
"separation": {
"type": "number"
},
"usable": {
"type": "boolean"
},
"verdict": {
"type": "string"
}
},
"required": [
"name",
"key",
"fill",
"distinct",
"separation",
"usable",
"verdict"
],
"additionalProperties": false
}
},
"curatorConfirmed": {
"type": "number"
},
"usableCount": {
"type": "number"
},
"inert": {
"type": "boolean"
}
},
"required": [
"property",
"published",
"dimensions",
"curatorConfirmed",
"usableCount",
"inert"
],
"additionalProperties": false
}
}
},
"required": [
"properties"
],
"$schema": "http://json-schema.org/draft-07/schema#",
"additionalProperties": false
}🟢vela.research.list_studies
List FieldStation research ideas as a library-kit DiscoveryDTO. Each card is a study we can support, not a running participant surface. The honesty gate (limitations, readiness, doNotClaim) is enforced by research:catalog-check — this tool publishes that same file. FREE and read-only. Presence is gated; truth is not. [capability: study-catalogue · mirrors: GET /api/research/studies]
输入模式
{
"type": "object",
"properties": {},
"$schema": "http://json-schema.org/draft-07/schema#"
}输出模式
{
"type": "object",
"properties": {
"ok": {
"type": "boolean",
"const": true
},
"note": {
"type": "string"
},
"problems": {
"type": "array",
"items": {
"type": "string"
}
},
"sendable": {
"type": "number"
},
"count": {
"type": "number"
},
"discovery": {
"type": "object",
"properties": {
"facetGroups": {
"type": "array",
"items": {
"type": "object",
"properties": {
"key": {
"type": "string"
},
"heading": {
"type": "string"
},
"combine": {
"type": "string",
"enum": [
"and",
"or"
]
},
"facets": {
"type": "array",
"items": {
"type": "object",
"properties": {
"value": {
"type": "string"
},
"label": {
"type": "string"
},
"count": {
"type": "number"
}
},
"required": [
"value",
"label",
"count"
],
"additionalProperties": false
}
}
},
"required": [
"key",
"heading",
"combine",
"facets"
],
"additionalProperties": false
}
},
"cards": {
"type": "array",
"items": {
"type": "object",
"properties": {
"id": {
"type": "string"
},
"href": {
"type": "string"
},
"eyebrow": {
"type": "string"
},
"title": {
"type": "string"
},
"claim": {
"type": "string"
},
"chips": {
"type": "array",
"items": {
"type": "object",
"properties": {
"slug": {
"type": "string"
},
"label": {
"type": "string"
}
},
"required": [
"slug",
"label"
],
"additionalProperties": false
}
}
},
"required": [
"id",
"href",
"eyebrow",
"title",
"claim"
],
"additionalProperties": false
}
},
"labels": {
"type": "object",
"properties": {
"filterHeading": {
"type": "string"
},
"clear": {
"type": "string"
},
"resultNoun": {
"type": "array",
"items": [
{
"type": "string"
},
{
"type": "string"
}
]
}
},
"required": [
"filterHeading",
"clear",
"resultNoun"
],
"additionalProperties": false
}
},
"required": [
"facetGroups",
"cards",
"labels"
],
"additionalProperties": false
},
"studies": {
"type": "array",
"items": {
"type": "object",
"properties": {
"id": {
"type": "string"
},
"title": {
"type": "string"
},
"claim": {
"type": "string"
},
"repo": {
"type": "string"
},
"readiness": {
"type": "string"
},
"ethicsBurden": {
"type": "string"
},
"stage": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
]
},
"disciplines": {
"type": "array",
"items": {
"type": "string"
}
},
"needs": {
"type": "array",
"items": {
"type": "string"
}
}
},
"required": [
"id",
"title",
"claim",
"repo",
"readiness",
"ethicsBurden",
"stage",
"disciplines",
"needs"
],
"additionalProperties": false
}
}
},
"required": [
"ok",
"note",
"problems",
"sendable",
"count",
"discovery",
"studies"
],
"$schema": "http://json-schema.org/draft-07/schema#",
"additionalProperties": false
}🟢vela.research.get_study(id)
One FieldStation study as a library-kit ProfileDTO plus the raw StudyRecord. Unknown id is an error. FREE and read-only. [capability: study-catalogue · mirrors: GET /api/research/studies/:id]
输入模式
{
"type": "object",
"properties": {
"id": {
"type": "string",
"minLength": 1,
"description": "Catalogue id, e.g. S-01."
}
},
"required": [
"id"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}输出模式
{
"type": "object",
"properties": {
"ok": {
"type": "boolean",
"const": true
},
"note": {
"type": "string"
},
"problems": {
"type": "array",
"items": {
"type": "string"
}
},
"profile": {
"type": "object",
"properties": {
"id": {
"type": "string"
},
"title": {
"type": "string"
},
"author": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
]
},
"year": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
]
},
"kicker": {
"type": "string"
},
"body": {
"type": "array",
"items": {
"type": "object",
"properties": {
"kind": {
"type": "string"
}
},
"required": [
"kind"
],
"additionalProperties": {}
}
},
"meta": {
"type": "object",
"properties": {
"title": {
"type": "string"
},
"description": {
"type": "string"
}
},
"required": [
"title",
"description"
],
"additionalProperties": false
}
},
"required": [
"id",
"title",
"author",
"year",
"kicker",
"body",
"meta"
],
"additionalProperties": {}
},
"study": {
"type": "object",
"properties": {
"id": {
"type": "string"
},
"title": {
"type": "string"
},
"claim": {
"type": "string"
}
},
"required": [
"id",
"title",
"claim"
],
"additionalProperties": {}
}
},
"required": [
"ok",
"note",
"problems",
"profile",
"study"
],
"$schema": "http://json-schema.org/draft-07/schema#",
"additionalProperties": false
}社区
证据
最近观测
已验证未记录版本9 个工具
已验证未记录版本8 个工具