study.vela/corpus

Est-ce que study.vela/corpus est sûr ?

Au dernier audit MCP Hub, le serveur MCP « study.vela/corpus » est classé « Non encore testé ». Référencé dans l'annuaire. Seul le pentest comportemental fait foi, et il n'a pas encore été exécuté sur ce serveur. Le verdict est réévalué en continu ; consultez la fiche pour l'état à jour.

Méthode : MCP Hub analyse la description de chaque outil (couche 1) et, pour le verdict fort, exécute le serveur dans une micro-VM isolée avec leurres et réseau bloqué (couche 2). On publie des noms et des compteurs, jamais le contenu brut renvoyé par un outil.

Les 10 outils

• vela.corpus.describe_topic≈ 584 tokens

  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]

  Paramètres, retour & exemple (1)

  Paramètres

  • topic · string · optionnel

  Exemple d'appel

  {"name": "vela.corpus.describe_topic", "arguments": {"topic": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"inUse": {}, "declared": {}}}

• vela.corpus.ground_claim≈ 394 tokens

  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]

  Paramètres, retour & exemple (2)

  Paramètres

  • claim · string · requis
    The claim to ground.
  • limit · integer · optionnel

  Exemple d'appel

  {"name": "vela.corpus.ground_claim", "arguments": {"claim": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"hits": [], "claim": "texte"}}

• vela.corpus.list_topics≈ 341 tokens

  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]

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "vela.corpus.list_topics", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"topics": []}}

• vela.corpus.query≈ 801 tokens

  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]

  Paramètres, retour & exemple (9)

  Paramètres

  • axes · object · optionnel
    Axis → allowed weights. ALL listed axes must match. e.g. {"religion":["T","s"],"work":["T","s"]}
  • text · string · optionnel
    Substring match over title / author / one-line claim.
  • genre · string · optionnel
  • limit · integer · optionnel
  • topic · string · optionnel
    Coordinate system to query (topic_configs.slug).
  • offset · integer · optionnel
  • themes · array · optionnel
    Cards citing ANY of these controlled themes.
  • qualities · array · optionnel
    Cards carrying ANY of these qualities (emotions, for being-human).
  • include_passages · boolean · optionnel
    Include theme-anchored passage pointers.

  Exemple d'appel

  {"name": "vela.corpus.query", "arguments": {"axes": {}, "text": "texte", "genre": "texte", "limit": 1, "topic": "texte", "offset": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"hits": [], "topic": "texte", "total": 1, "applied": {}, "returned": 1, "truncated": true}}

• vela.corpus.witness≈ 882 tokens

  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]

  Paramètres, retour & exemple (7)

  Paramètres

  • axes · object · optionnel
    Axis weight filters for claims only — same format as vela.corpus.query (e.g. {work:["T","s"]}).
  • themes · array · optionnel
    Controlled themes from Vela's vocabulary (e.g. 'fairness', 'recognition').
  • emotions · array · optionnel
    Emotions to match (e.g. 'shame', 'betrayal', 'grief'). At least one of themes or emotions is required.
  • max_claims · integer · optionnel
    Max one-line claims to return (default 3).
  • max_passages · integer · optionnel
    Max passages to return (default 5).
  • problem_slug · string · optionnel
    ProblemFrame entity slug (echoed in response; reserved for frame_tags[] pre-cache after PA-1153 ID-freeze).
  • condition_slug · string · optionnel
    ConditionFrame entity slug (same reservation as problem_slug).

  Exemple d'appel

  {"name": "vela.corpus.witness", "arguments": {"axes": {}, "themes": [], "emotions": [], "max_claims": 1, "max_passages": 1, "problem_slug": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"query": {}, "claims": [], "passages": [], "evidence_grade": "texte"}}

• vela.library.reading_list≈ 459 tokens

  The reading list an emotion or theme page shows: books with one-line claims and a short attributed passage (≤300 chars). Exactly one of emotion or theme. FREE and read-only. Every url carries ?ref=mcp for citation arrival measurement. [capability: library-extraction-cards · mirrors: GET /api/corpus/reading-list]

  Paramètres, retour & exemple (3)

  Paramètres

  • limit · integer · optionnel
  • theme · string · optionnel
    Controlled theme slug (e.g. desire). Mutually exclusive with emotion.
  • emotion · string · optionnel
    Emotion primary slug (e.g. grief). Mutually exclusive with theme.

  Exemple d'appel

  {"name": "vela.library.reading_list", "arguments": {"limit": 1, "theme": "texte", "emotion": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"ok": true, "kind": "emotion", "rows": [], "slug": "texte", "limit": 1}}

• vela.magazine.relation_floor≈ 442 tokens

  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]

  Paramètres, retour & exemple (1)

  Paramètres

  • property · string · optionnel
    Restrict to one property id; omit for every property with published pieces.

  Exemple d'appel

  {"name": "vela.magazine.relation_floor", "arguments": {"property": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"properties": []}}

• vela.magazine.sequence_path≈ 435 tokens

  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]

  Paramètres, retour & exemple (4)

  Paramètres

  • forms · array · optionnel
    Article forms to steer by. At least one of emotions/forms is required.
  • limit · integer · optionnel
    Pieces to return (default 4).
  • emotions · array · optionnel
    Emotions the reader is steering by.
  • property · string · optionnel
    Property id; defaults to vela.

  Exemple d'appel

  {"name": "vela.magazine.sequence_path", "arguments": {"forms": [], "limit": 1, "emotions": [], "property": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"path": [], "property": "texte"}}

• vela.research.get_study≈ 446 tokens

  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]

  Paramètres, retour & exemple (1)

  Paramètres

  • id · string · requis
    Catalogue id, e.g. S-01.

  Exemple d'appel

  {"name": "vela.research.get_study", "arguments": {"id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"ok": true, "note": "texte", "study": {}, "profile": {}, "problems": []}}

• vela.research.list_studies≈ 770 tokens

  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]

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "vela.research.list_studies", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"ok": true, "note": "texte", "count": 1, "studies": [], "problems": [], "sendable": 1, "discovery": {}}}

C'est votre serveur ?

Revendiquez-le sur l'espace créateur (preuve GitHub, domaine ou npm) pour afficher le badge « propriétaire vérifié » et lancer un pentest comportemental à la demande afin d'obtenir le badge « Vérifié ».

Créer un compte / revendiquer →

Source

https://vela.study/mcp