guide.bicycle/guide-registry

Est-ce que guide.bicycle/guide-registry est sûr ?

Au dernier audit MCP Hub, le serveur MCP « guide.bicycle/guide-registry » 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

• get_answer≈ 214 tokens

  Get one Answer — question, grounded answer, visible citations — by id or slug, in the Answer contract v0 shape (ANSWERS-PROGRAM.md). Read-only. Returns null if not found.

  Paramètres, retour & exemple (1)

  Paramètres

  • id · string · requis
    The Answer's stable id or slug.

  Exemple d'appel

  {"name": "get_answer", "arguments": {"id": "texte"}}

  Exemple de retour

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

• get_guide≈ 192 tokens

  Get one guide's registry row by slug, with its artifact + routing-surface status.

  Paramètres, retour & exemple (1)

  Paramètres

  • slug · string · requis
    The guide slug, e.g. start-a-company.

  Exemple d'appel

  {"name": "get_guide", "arguments": {"slug": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"guide": {}, "api_version": "texte"}}

• list_answers≈ 247 tokens

  List Answers (contract v0), paginated with an opaque cursor. Read-only.

  Paramètres, retour & exemple (2)

  Paramètres

  • limit · integer · optionnel
    Max answers to return (default: loader's choice, capped 200).
  • cursor · string · optionnel
    Opaque pagination cursor from a previous list_answers call's nextCursor.

  Exemple d'appel

  {"name": "list_answers", "arguments": {"limit": 1, "cursor": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"items": [], "nextCursor": "texte"}}

• list_capabilities≈ 786 tokens

  Traverse the capability spine joining books, guides (capability packages), KSAO-grade elements and jobs. Use min_guides=2 for the cross-cutting capabilities that span many guides, role=<role> for what a job requires, capability_detail=<slug> for one package with its elements and books hydrated. ksao_type/canon_component_id are null by design where unresolved — treat null as 'not yet joined', never as 'no link'.

  Paramètres, retour & exemple (12)

  Paramètres

  • q · string · optionnel
    Substring match on the element label.
  • role · string · optionnel
    Elements required by this job role, e.g. compensation-analyst.
  • limit · number · optionnel
    Cap the rows returned (default 200). `total` always reports the true count.
  • has_job · boolean · optionnel
    Only elements that some job requires (via a career guide).
  • ksao_type · string · optionnel
    knowledge | skill | ability | other — from a panel validated at 95.1% on gold O*NET labels. 'other' is UNVALIDATED (no gold labels existed for it).
  • capability · string · optionnel
    Elements taught by this capability (guide slug).
  • min_guides · number · optionnel
    Only elements taught by >= N capabilities. 2 gives the cross-cutting spine.
  • conflicting · boolean · optionnel
    Only elements where 2+ non-career guides define the same label differently — these need a ruling.
  • construct_class · string · optionnel
    person-attribute (knowledge/skill/ability — what a JOB requires and a learner develops) | condition-or-outcome (what a capability PRODUCES, e.g. 'Retention & Workforce Stability'). Only ~30% of elements are person attributes — filter to these for 'what does this role need'.
  • capability_detail · string · optionnel
    Return ONE capability with its elements and books hydrated, instead of querying elements.
  • has_canon_identity · boolean · optionnel
    true = only elements resolved to a JobFrame canon component (an IDENTITY, panel-adjudicated). false = only unresolved.
  • canon_promotion_candidate · boolean · optionnel
    true = only elements the JobFrame canon has NO component for. This is a real answer, not a failed lookup — these are the constructs to PROMOTE into the canon.

  Exemple d'appel

  {"name": "list_capabilities", "arguments": {"q": "texte", "role": "texte", "limit": 1, "has_job": true, "ksao_type": "texte", "capability": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"total": 1, "elements": [], "returned": 1, "capability": {}, "spine_meta": "texte", "api_version": "texte"}}

• list_conditions≈ 636 tokens

  List organizational conditions (identity, label, guide count, causal-role counts). Filter by draft domain, subdomain, or causal_role (driver|mediator|outcome). Names and counts only — no addresses, no passages.

  Paramètres, retour & exemple (6)

  Paramètres

  • q · string · optionnel
    Substring match on the condition label.
  • id · string · optionnel
    Exact condition_identity_id. When set, other filters are ignored.
  • limit · number · optionnel
    Cap rows returned. Default 100, max 500.
  • domain · string · optionnel
    Draft domain slug, e.g. organizational-structure-and-culture.
  • subdomain · string · optionnel
    Draft sub-domain slug, e.g. organizational-learning-and-improvement.
  • causal_role · string · optionnel
    driver | mediator | outcome. Unknown values match nothing.

  Exemple d'appel

  {"name": "list_conditions", "arguments": {"q": "texte", "id": "texte", "limit": 1, "domain": "texte", "subdomain": "texte", "causal_role": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"count": 1, "filters": {}, "taxonomy": {}, "conditions": [], "api_version": "texte", "address_status": "texte", "total_matching": 1}}

• list_disagreements≈ 516 tokens

  Where does the field disagree? Returns cross-book tension names and the books on each pole (title, author, library_id) plus the guide URL. Filter by slug, persona, or category. Names and provenance only — no passages.

  Paramètres, retour & exemple (4)

  Paramètres

  • slug · string · optionnel
    One guide, e.g. start-a-company. When set, persona/category are ignored.
  • limit · number · optionnel
    Cap rows returned. Default 100, max 500.
  • persona · string · optionnel
    Audience filter, e.g. people-analytics-professional.
  • category · string · optionnel
    Subject shelf, e.g. field, skills, analytics.

  Exemple d'appel

  {"name": "list_disagreements", "arguments": {"slug": "texte", "limit": 1, "persona": "texte", "category": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"count": 1, "filters": {}, "api_version": "texte", "disagreements": [], "total_matching": 1}}

• list_guides≈ 1063 tokens

  List the bicycle.guide registry — every guide's home, status, access, standard, syndication and grounding, plus the distribution roll-up (including guides homed to a property with no rendering surface).

  Paramètres, retour & exemple (13)

  Paramètres

  • home · string · optionnel
    Filter by owning property, e.g. jobframe, peopleanalyst, penwright.
  • limit · number · optionnel
    Cap the rows returned. Default 100, max 500.
  • access · string · optionnel
    Filter by access: free | gated.
  • domain · string · optionnel
    Filter by life-domain — the layer ABOVE the subject shelf: work | life | play. Derived from the guide's category via content/registry/shelves.json. `rollup.by_domain` lists them.
  • fields · string · optionnel · compact | full
    Row shape. "compact" returns only slug/title/home/status/access/price_cents/has_artifact/category/domain/personas/canonical_url — no rollup, no registry_meta. "full" returns the entire decorated registry row plus the rollup and registry_meta, as before. Default over this server: "compact".
  • series · string · optionnel
    Filter by guide series — the operational grouping of guides made to be used together, e.g. competencies, penwright-writing, startup-journey, ladder:hr-business-partner.
  • status · string · optionnel
    Filter by status: on | draft.
  • persona · string · optionnel
    Filter by the audience a guide serves, e.g. people-analytics-professional, aspiring-author, executive-performance-leader. A guide can serve several; this matches any of them.
  • category · string · optionnel
    Filter by subject shelf — the reader-facing topic axis, e.g. field, skills, analytics, writing, comp. Matches the primary category OR a cross-shelf tag.
  • standard · string · optionnel
    Filter by standard: bicycle | life-stage | problem-opportunity.
  • guide_type · string · optionnel
    Filter by guide CLASS: career (level-based job guides, their own program) | capability | book_profile. Combine with series=ladder:<role> to get one role's whole ladder.
  • has_artifact · boolean · optionnel
    Only guides that do (true) / do not (false) have a new-design artifact.
  • home_unrouted · boolean · optionnel
    Only guides whose home has NO rendering surface at all (the distribution gap).

  Exemple d'appel

  {"name": "list_guides", "arguments": {"home": "texte", "limit": 1, "access": "texte", "domain": "texte", "fields": "compact", "series": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"count": 1, "limit": "texte", "fields": "compact", "guides": [], "rollup": {}, "filters": {}, "api_version": "texte", "registry_meta": "texte", "total_matching": 1}}

• list_taxonomy≈ 451 tokens

  Get the bicycle.guide vocabulary — domains, shelves (with live guide counts), series, personas, guide_types, and the classification conventions (pillar/spoke, discriminant home, bicycle-guide-serves-all) as machine-readable data rather than prose.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "list_taxonomy", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"series": [], "domains": [], "shelves": [], "personas": [], "api_version": "texte", "conventions": {}, "guide_types": [], "counts_basis": {}, "unclassified": {}, "registry_meta": "texte"}}

• search_answers≈ 241 tokens

  Search Answers by free-text query over question/answer text. Returns contract v0 records. Read-only.

  Paramètres, retour & exemple (2)

  Paramètres

  • limit · integer · optionnel
    Max results to return (default: loader's choice, capped 200).
  • query · string · requis
    Free-text query matched against question/answer text.

  Exemple d'appel

  {"name": "search_answers", "arguments": {"query": "texte"}}

  Exemple de retour

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

• search_guides≈ 696 tokens

  Search published guides by topic. Returns matches, or a structured refusal with the nearest owned guides and the missing topic. No model call. Filter by persona or category.

  Paramètres, retour & exemple (4)

  Paramètres

  • q · string · requis
    Topic or question in plain language. No model call — matched against registry taxonomy and the capability spine.
  • limit · number · optionnel
    Cap hits returned. Default 10, max 20.
  • persona · string · optionnel
    Audience filter. A miss that fails this rule is a structured refusal.
  • category · string · optionnel
    Subject shelf filter. A miss that fails this rule is a structured refusal.

  Exemple d'appel

  {"name": "search_guides", "arguments": {"q": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"query": "texte", "guides": [], "covered": true, "filters": {}, "nearest": [], "suggest": [], "api_version": "texte", "missing_topic": "texte"}}

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://bicycle.guide/mcp