guide.strengthtraining/guide-registry

Measured conclusion: Alive, not deep-tested. L2 outcome: not_attempted.

Read-only Bicycle Guide registry: published guides, homes, taxonomy, capability spine. No auth.

Add to your agent

Copy this into your MCP client config:

{
  "mcpServers": {
    "guide-registry": {
      "url": "https://strengthtraining.guide/mcp",
      "transport": "streamable-http"
    }
  }
}

Measured tools (10)

• list_guides read-only

  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).

  Parameters:

  • home — string — Filter by owning property, e.g. jobframe, peopleanalyst, penwright.
  • limit — number — Cap the rows returned. Default 100, max 500.
  • access — string — Filter by access: free | gated.
  • domain — string — 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 — 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 — 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 — Filter by status: on | draft.
  • persona — string — 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 — 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 — Filter by standard: bicycle | life-stage | problem-opportunity.
  • guide_type — string — 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 — Only guides that do (true) / do not (false) have a new-design artifact.
  • home_unrouted — boolean — Only guides whose home has NO rendering surface at all (the distribution gap).

  Hints: read-only yes · destructive no · idempotent not declared · open-world no

• get_guide read-only

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

  Parameters:

  • slug (required) — string — The guide slug, e.g. start-a-company.

  Hints: read-only yes · destructive no · idempotent not declared · open-world no

• list_taxonomy read-only

  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.

  Hints: read-only yes · destructive no · idempotent not declared · open-world no

• list_capabilities read-only

  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'.

  Parameters:

  • q — string — Substring match on the element label.
  • role — string — Elements required by this job role, e.g. compensation-analyst.
  • limit — number — Cap the rows returned (default 200). `total` always reports the true count.
  • has_job — boolean — Only elements that some job requires (via a career guide).
  • ksao_type — string — 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 — Elements taught by this capability (guide slug).
  • min_guides — number — Only elements taught by >= N capabilities. 2 gives the cross-cutting spine.
  • conflicting — boolean — Only elements where 2+ non-career guides define the same label differently — these need a ruling.
  • construct_class — string — 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 — Return ONE capability with its elements and books hydrated, instead of querying elements.
  • has_canon_identity — boolean — true = only elements resolved to a JobFrame canon component (an IDENTITY, panel-adjudicated). false = only unresolved.
  • canon_promotion_candidate — boolean — 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.

  Hints: read-only yes · destructive no · idempotent not declared · open-world no

• search_guides read-only

  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.

  Parameters:

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

  Hints: read-only yes · destructive no · idempotent not declared · open-world no

• list_disagreements read-only

  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.

  Parameters:

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

  Hints: read-only yes · destructive no · idempotent not declared · open-world no

• list_conditions read-only

  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.

  Parameters:

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

  Hints: read-only yes · destructive no · idempotent not declared · open-world no

• get_answer read-only

  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.

  Parameters:

  • id (required) — string — The Answer's stable id or slug.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• list_answers read-only

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

  Parameters:

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

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• search_answers read-only

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

  Parameters:

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

  Hints: read-only yes · destructive no · idempotent yes · open-world no

Publisher website Repository

Measured by MCPYP probing. Untested fields are omitted, never estimated. Listing is always free; MCPYP never proxies calls or stores user tokens.