"Doctrine" matching MCP tools:

• doctrineA

  Vigi-SkyA

  Return Vigi-Sky's identity card and method rules: founder, launch date, the book, the 'never UFO detected' rule, and the difference between the imported Hatch archive (18,116 historical cases) and Vigi-Sky's own public case files. Use it before describing Vigi-Sky or explaining its method; its counts are fixed at release, so for current numbers and API health use status, and for a page to cite use cite.

  ConnectorNo auth

• search_opinionsA

  Court ListenerA

  Search US court opinions from CourtListener — 8.3 million of them, with no API key and no rate limit. Covers the UNITED STATES SUPREME COURT (SCOTUS), the federal circuit courts of appeals, the federal district courts, and the state courts (71% of the corpus is state case law). THE tool for what a US court HELD, decided or ruled in a NAMED CASE — "What did the Supreme Court hold in Air France v. Saks?", "Miranda v. Arizona", "the Ninth Circuit ruling in ..." — including the treaty and statutory questions such cases turn on (Warsaw Convention, ERISA, the Fourth Amendment). Matches the case name, the judge, and (where CourtListener recorded one) a nature-of-suit/disposition category, so it is strongest on party names, judges, and case categories ("workers compensation", "habeas", "immigration") and weaker on a legal DOCTRINE that would not appear in those fields (e.g. "qualified immunity") — use find_case when you know the party, and expect this to sometimes miss on doctrine-only phrasing. Filter by jurisdiction (state vs federal, inferred from the citation reporter) and by date_filed (the real ruling date). A specific court code (e.g. "scotus", "ca9") or a filing after the covered window falls back to a live, token-less CourtListener search automatically. Every result carries snapshot_date and opinion_ids to read with get_opinion.

  ConnectorNo auth

• architect.validateA

  AI Design BlueprintA

  Pro/Teams: first-pass doctrine review of agentic code/workflow against the 10-principle AI Design Blueprint doctrine. ON CLIENT TIMEOUT: DO NOT RETRY THIS TOOL. Long-running LLM call (60-180s typical); MCP clients commonly close the call before the server returns. Retrying re-runs the 60-180s LLM call from scratch and burns compute. RECOVERY: the run_id is emitted in the FIRST notifications/progress event at t=0s (before the LLM call begins), capture it. On timeout, call `me.validation_history(run_id='<that-id>')` to fetch the persisted result; the server-side run completes independently within a 6-minute budget. Edge case: if the connection closed before the first progress notification (very rare; sub-second window), call `me.validation_history(repository='<same value you passed here>')` to find your most recent run. TASK-AUGMENTED INVOCATION (MCP 2025-11-25, SEP-1686): clients that advertise the `tasks` capability can task-augment this call by including `task: {ttl: <ms>}` inside the JSON-RPC request's `params` (NOT as a tool argument; alongside `arguments`, `_meta`, etc.). The server returns a `CreateTaskResult` immediately (taskId equals the run_id above) and runs the validation in the background. Spec-correct long-running pattern: poll via `tasks/get` for state, fetch the terminal payload via `tasks/result`, listen for `notifications/tasks/status` for push updates, and cancel via `tasks/cancel`. `_meta.progressToken` from the original request stays valid for the entire task lifetime. Sync (non-augmented) calls behave exactly as before, backwards-compatible by construction. The me.validation_history(run_id=...) recovery path remains the canonical recovery handle for clients that don't yet advertise the tasks capability. Returns code_classification (autonomous_agentic_workflow vs non_agentic_component), per-principle findings (verdict, severity_score 0-100, severity_class, code-cited evidence, recommendation), severity-weighted readiness (score|null, grade|null, tier ∈ {production_ready, emerging, draft, not_applicable}), recommended examples, reproducibility envelope (model, seed, doctrine_fingerprint, prompt_template_fingerprint), persistence_status with shareable run_id/badge_url/review_url. Those two URLs 404 until the run's owner publishes it: runs are private by default. Read `public_review` in the response before embedding either one. WHEN TO CALL: the user wants a governance audit, readiness score, or production_ready badge on an agent/workflow they just built or changed. WHEN NOT TO CALL: non-agentic plumbing (math utilities, type aliases, event-loop helpers, single-shot request/response handlers) returns tier=not_applicable with score=null/grade=null, that's not a failure, the doctrine simply doesn't grade non-agentic code, and architect.certify will refuse with not_agentic_component. Submit the OWNING agentic workflow instead. BEHAVIOR: long-running LLM call (~60-180s typical at high reasoning effort, single-pass; server-side budget 6 min). Mints run_id at t=0; first notifications/progress event carries run_id as recovery handle; keepalive every 30s. Persists ValidationRun + UserValidationRun + AIValidationRunLog + LLMUsageLog atomically; on rollback, badge/review URLs are stripped. Auth: sign-in required, with an active Pro, Pro Plus, Teams, Enterprise, beta, or trial plan. Data at rest in the UK; OpenAI (US) processing (no-training); prompt-injection in code is inert. INPUTS: send FULL file contents verbatim as `implementation_context` (NO truncation, NO `...` placeholders, NO comment removal, the architect treats your `...` as literal code and hallucinates bugs that don't exist). If too large, split into MULTIPLE calls scoped by file/module; never truncate one call. When one call carries several files, keep each file whole, its own import lines included: merging files under one shared import block reads as code that uses names it never imported, and is reported as a defect. Pass repository="<name>" to group runs into a project trend. Pass private_session=true to skip the stored run (persistence + recovery disabled); operational security + cost logs are still kept. focus_area narrows scope; unmatched focus_area fails explicitly rather than silently widening. PAYLOAD COMPLETENESS (load-bearing if you intend to architect.certify this run): the validate first-pass is permissive, it scores on doctrine alignment + structural patterns visible in the submitted code. Cert's adversarial second-pass is rigorous: it scores on cert-payload-completeness as well as code correctness. A run that scores 100/A at validate can cert-reject pre-LLM with `payload_incomplete` when imported modules' surfaces aren't visible. To validate with INTENT TO CERT, also bundle verbatim public-surface stubs for every imported module: `from sqlalchemy.exc import SQLAlchemyError` → include a stub class; `from app.db import models` → include a `class models:` namespace stub with the columns/methods the code references; module-level imports of `dataclass`, `Literal`, `json`, `datetime`, `timezone` MUST also be in the payload (cert correctly catches when they're omitted, the module would NameError on import as submitted). 'Submit Like Production': the payload should be the code as it would actually run. TWO COMPLETENESS AXES. (1) IMPORTS: stub the public surface of every dependency (above). (2) ENFORCEMENT BRANCHES: the code under cert itself (approval gates, policy checks, recovery paths) must be the REAL logic, fully written. A placeholder body (`# ... execute approved action ...`, `pass # TODO`, a bare `...`) is graded as a MISSING control, not shorthand; cert scores what would actually run. Never sketch the agent you are certifying. Empirically reconfirmed PR #157 iter8 → iter9 cert downgrades. SCORE VARIANCE DISCLOSURE (anomaly #10: empirically documented): validate scores are POINT ESTIMATES with an observed empirical variance band of ~20-67 pts on BYTE-IDENTICAL input. Runs against the same repository, same code, same deterministic seed (the seed is derived from input: same input → same seed) can produce materially different scores AND different top-blocker rankings, because OpenAI's reasoning models at reasoning_effort=high are not strictly deterministic even with the seed parameter pinned. The `reproducibility_mode='best_effort'` field on every response is the platform's honest disclosure of this property. For decisions where stability matters more than speed, call `architect.validate_consensus` (N=3-5 aggregated, median verdict + per-principle stability metrics) instead: collapses the variance, surfaces unstable principles explicitly. A single validate run is a single roll; consensus is the right tool when one score isn't enough. ITERATION LOOP: repository keying. Pass the SAME `repository` value across calls to chain iteration rounds; the validator auto-resolves the most recent prior run on (user, repository, scope) as `prior_run_baseline` and the LLM grades the new submission with iteration context (per-principle severity deltas surface in the response). Changing the `repository` string between calls, even subtly with an `iter-2` suffix, silently severs the chain and yields a fresh blind first-shot. Round numbering belongs in `task` or commit messages, never in `repository`. See the `architect-validation-orchestration` skill in the agent-asset pack for the full validate → consensus → certify sequence. VERIFICATION LAYERS (the two-layer doctrine this platform practices on itself): validate verifies DOCTRINE ALIGNMENT against the 10-principle Blueprint, design patterns, hand-off explicitness, operational-state inspectability, race/blocker handling at the architectural level. validate does NOT guarantee runtime correctness. cert verifies PAYLOAD COMPLETENESS and runs an adversarial second pass over the submitted code: catches production_blockers the first pass missed, name-errors on import, missing module surfaces, etc. cert does NOT verify runtime correctness either. Passing validate is a NECESSARY condition for production_ready, not a sufficient one. Runtime correctness (does this actually execute and behave?) is verified at the THIRD layer: your tests, types, walks. The platform's own recursive-integrity practice: every PR runs validate against its own primitives, then cert. Real bugs surfaced via this practice in PR #157, NULL-UUID false-positive (iter3) and tie-breaker mismatch (iter5), that 25 unit tests had missed. Two-layer verification is the discipline, not 'either/or'. TYPED FAILURES (the top-level error.code; error.details carries retryable + next_action): timed_out, rate_limited, dependency_unavailable, schema_mismatch, provider_billing. NEXT STEP: if tier=production_ready (A or B grade), the response carries certification_status='not_evaluated', call architect.certify(run_id, code) to mint the certified production_ready badge (separate ~60-150s adversarial review, eligibility-gated). See Payload Completeness above for the common pre-cert pitfall.

  ConnectorNo auth

• design.validateA

  AI Design BlueprintA

  Pro/Teams: first-pass surface-craft review of a FRONTEND artefact (component, screen, or flow) against the 8 laws of the Experience Design Blueprint. The surface-craft companion to architect.validate: where architect.validate scores agentic ARCHITECTURE against the 10 agentic principles, design.validate scores the PERCEPTIBLE SURFACE, what the user sees, taps, scans, and remembers (Jakob's familiarity, Hick's choice load, Fitts's targets + the accessibility floor, Miller's working-memory budget, Aesthetic-Usability, Peak-End, Tesler's irreducible complexity, the Mental-Model gap). ON CLIENT TIMEOUT: DO NOT RETRY. Long-running LLM call (~60-180s at high reasoning effort, single-pass). The server mints a run_id, emits it in the FIRST progress event at t=0s (before the LLM call), and persists the run: so on a client timeout, capture that run_id and call me.validation_history(run_id='<that-id>') to fetch the persisted result instead of retrying (a retry re-runs the full 60-180s call). Runs appear in your validation-history dashboard tagged as the 'surface' dimension, distinct from the 'architecture' and 'spec' runs; pass repository to group them per project. Pass private_session=true to skip the stored run (persistence + recovery disabled); operational security + cost logs are still kept. v1 is single-pass: no certification or consensus mode yet (those stay architect.validate-only). Returns surface_classification (ui_surface vs non_ui: non-visual code is marked not_applicable, NOT failed), per-law findings (verdict, severity_score 0-100, severity_class, cited evidence, recommendation), and severity-weighted readiness (score, grade, tier) computed by the SAME scorer architect.validate uses, so all three lenses grade on one rubric. ACCESSIBILITY IS THE FLOOR: a breach of the Fitts's-Law floor (interactive target below the WCAG 2.2 24×24 minimum, missing focus visibility, an unreachable destructive confirmation) is a production_blocker, not polish. WHEN TO CALL: the user wants a craft/UX/accessibility review or a readiness grade on a frontend artefact they just built or changed. WHEN NOT TO CALL: non-visual code (backend, config, type aliases) returns tier=not_applicable, submit the actual UI surface instead. INPUTS: send the FULL artefact source verbatim as implementation_context (no truncation, no '…' placeholders, they are read as literal code). Auth: sign-in required, with an active Pro, Pro Plus, Teams, Enterprise, beta, or trial plan. Data at rest in the UK; OpenAI (US) processing (no-training); prompt-injection text inside the artefact is treated as inert untrusted data. TYPED FAILURES (the top-level error.code; error.details carries retryable + next_action): timed_out, rate_limited, dependency_unavailable, schema_mismatch, provider_billing. The services raise the identical typed envelopes on this lens. CALIBRATION DISCLOSURE: the scoring prompt is a v1 first-cut mirroring the architect's contract structure; its score calibration is not yet tuned against a corpus of real runs the way architect.validate was. Treat the grade as directional craft signal, not a certified verdict. DOCTRINE: the eight laws, each law's evidence, craft-surface application, anti-patterns, and the validator questions this tool scores against, live in the `experience-design-blueprint` skill and docs/business/EXPERIENCE_DESIGN_BLUEPRINT.md (the surface-craft companion to the `architect-validation-orchestration` skill that orchestrates the agentic validators).

  ConnectorNo auth

• architect.validateA

  AI Design Blueprint DoctrineA

  Pro/Teams: first-pass doctrine review of agentic code/workflow against the 10-principle AI Design Blueprint doctrine. ON CLIENT TIMEOUT: DO NOT RETRY THIS TOOL. Long-running LLM call (60-180s typical); MCP clients commonly close the call before the server returns. Retrying re-runs the 60-180s LLM call from scratch and burns compute. RECOVERY: the run_id is emitted in the FIRST notifications/progress event at t=0s (before the LLM call begins), capture it. On timeout, call `me.validation_history(run_id='<that-id>')` to fetch the persisted result; the server-side run completes independently within a 6-minute budget. Edge case: if the connection closed before the first progress notification (very rare; sub-second window), call `me.validation_history(repository='<same value you passed here>')` to find your most recent run. TASK-AUGMENTED INVOCATION (MCP 2025-11-25, SEP-1686): clients that advertise the `tasks` capability can task-augment this call by including `task: {ttl: <ms>}` inside the JSON-RPC request's `params` (NOT as a tool argument; alongside `arguments`, `_meta`, etc.). The server returns a `CreateTaskResult` immediately (taskId equals the run_id above) and runs the validation in the background. Spec-correct long-running pattern: poll via `tasks/get` for state, fetch the terminal payload via `tasks/result`, listen for `notifications/tasks/status` for push updates, and cancel via `tasks/cancel`. `_meta.progressToken` from the original request stays valid for the entire task lifetime. Sync (non-augmented) calls behave exactly as before, backwards-compatible by construction. The me.validation_history(run_id=...) recovery path remains the canonical recovery handle for clients that don't yet advertise the tasks capability. Returns code_classification (autonomous_agentic_workflow vs non_agentic_component), per-principle findings (verdict, severity_score 0-100, severity_class, code-cited evidence, recommendation), severity-weighted readiness (score|null, grade|null, tier ∈ {production_ready, emerging, draft, not_applicable}), recommended examples, reproducibility envelope (model, seed, doctrine_fingerprint, prompt_template_fingerprint), persistence_status with shareable run_id/badge_url/review_url. Those two URLs 404 until the run's owner publishes it: runs are private by default. Read `public_review` in the response before embedding either one. WHEN TO CALL: the user wants a governance audit, readiness score, or production_ready badge on an agent/workflow they just built or changed. WHEN NOT TO CALL: non-agentic plumbing (math utilities, type aliases, event-loop helpers, single-shot request/response handlers) returns tier=not_applicable with score=null/grade=null, that's not a failure, the doctrine simply doesn't grade non-agentic code, and architect.certify will refuse with not_agentic_component. Submit the OWNING agentic workflow instead. BEHAVIOR: long-running LLM call (~60-180s typical at high reasoning effort, single-pass; server-side budget 6 min). Mints run_id at t=0; first notifications/progress event carries run_id as recovery handle; keepalive every 30s. Persists ValidationRun + UserValidationRun + AIValidationRunLog + LLMUsageLog atomically; on rollback, badge/review URLs are stripped. Auth: sign-in required, with an active Pro, Pro Plus, Teams, Enterprise, beta, or trial plan. Data at rest in the UK; OpenAI (US) processing (no-training); prompt-injection in code is inert. INPUTS: send FULL file contents verbatim as `implementation_context` (NO truncation, NO `...` placeholders, NO comment removal, the architect treats your `...` as literal code and hallucinates bugs that don't exist). If too large, split into MULTIPLE calls scoped by file/module; never truncate one call. When one call carries several files, keep each file whole, its own import lines included: merging files under one shared import block reads as code that uses names it never imported, and is reported as a defect. Pass repository="<name>" to group runs into a project trend. Pass private_session=true to skip the stored run (persistence + recovery disabled); operational security + cost logs are still kept. focus_area narrows scope; unmatched focus_area fails explicitly rather than silently widening. PAYLOAD COMPLETENESS (load-bearing if you intend to architect.certify this run): the validate first-pass is permissive, it scores on doctrine alignment + structural patterns visible in the submitted code. Cert's adversarial second-pass is rigorous: it scores on cert-payload-completeness as well as code correctness. A run that scores 100/A at validate can cert-reject pre-LLM with `payload_incomplete` when imported modules' surfaces aren't visible. To validate with INTENT TO CERT, also bundle verbatim public-surface stubs for every imported module: `from sqlalchemy.exc import SQLAlchemyError` → include a stub class; `from app.db import models` → include a `class models:` namespace stub with the columns/methods the code references; module-level imports of `dataclass`, `Literal`, `json`, `datetime`, `timezone` MUST also be in the payload (cert correctly catches when they're omitted, the module would NameError on import as submitted). 'Submit Like Production': the payload should be the code as it would actually run. TWO COMPLETENESS AXES. (1) IMPORTS: stub the public surface of every dependency (above). (2) ENFORCEMENT BRANCHES: the code under cert itself (approval gates, policy checks, recovery paths) must be the REAL logic, fully written. A placeholder body (`# ... execute approved action ...`, `pass # TODO`, a bare `...`) is graded as a MISSING control, not shorthand; cert scores what would actually run. Never sketch the agent you are certifying. Empirically reconfirmed PR #157 iter8 → iter9 cert downgrades. SCORE VARIANCE DISCLOSURE (anomaly #10: empirically documented): validate scores are POINT ESTIMATES with an observed empirical variance band of ~20-67 pts on BYTE-IDENTICAL input. Runs against the same repository, same code, same deterministic seed (the seed is derived from input: same input → same seed) can produce materially different scores AND different top-blocker rankings, because OpenAI's reasoning models at reasoning_effort=high are not strictly deterministic even with the seed parameter pinned. The `reproducibility_mode='best_effort'` field on every response is the platform's honest disclosure of this property. For decisions where stability matters more than speed, call `architect.validate_consensus` (N=3-5 aggregated, median verdict + per-principle stability metrics) instead: collapses the variance, surfaces unstable principles explicitly. A single validate run is a single roll; consensus is the right tool when one score isn't enough. ITERATION LOOP: repository keying. Pass the SAME `repository` value across calls to chain iteration rounds; the validator auto-resolves the most recent prior run on (user, repository, scope) as `prior_run_baseline` and the LLM grades the new submission with iteration context (per-principle severity deltas surface in the response). Changing the `repository` string between calls, even subtly with an `iter-2` suffix, silently severs the chain and yields a fresh blind first-shot. Round numbering belongs in `task` or commit messages, never in `repository`. See the `architect-validation-orchestration` skill in the agent-asset pack for the full validate → consensus → certify sequence. VERIFICATION LAYERS (the two-layer doctrine this platform practices on itself): validate verifies DOCTRINE ALIGNMENT against the 10-principle Blueprint, design patterns, hand-off explicitness, operational-state inspectability, race/blocker handling at the architectural level. validate does NOT guarantee runtime correctness. cert verifies PAYLOAD COMPLETENESS and runs an adversarial second pass over the submitted code: catches production_blockers the first pass missed, name-errors on import, missing module surfaces, etc. cert does NOT verify runtime correctness either. Passing validate is a NECESSARY condition for production_ready, not a sufficient one. Runtime correctness (does this actually execute and behave?) is verified at the THIRD layer: your tests, types, walks. The platform's own recursive-integrity practice: every PR runs validate against its own primitives, then cert. Real bugs surfaced via this practice in PR #157, NULL-UUID false-positive (iter3) and tie-breaker mismatch (iter5), that 25 unit tests had missed. Two-layer verification is the discipline, not 'either/or'. TYPED FAILURES (the top-level error.code; error.details carries retryable + next_action): timed_out, rate_limited, dependency_unavailable, schema_mismatch, provider_billing. NEXT STEP: if tier=production_ready (A or B grade), the response carries certification_status='not_evaluated', call architect.certify(run_id, code) to mint the certified production_ready badge (separate ~60-150s adversarial review, eligibility-gated). See Payload Completeness above for the common pre-cert pitfall.

  ConnectorNo auth

• design.validateA

  AI Design Blueprint DoctrineA

  Pro/Teams: first-pass surface-craft review of a FRONTEND artefact (component, screen, or flow) against the 8 laws of the Experience Design Blueprint. The surface-craft companion to architect.validate: where architect.validate scores agentic ARCHITECTURE against the 10 agentic principles, design.validate scores the PERCEPTIBLE SURFACE, what the user sees, taps, scans, and remembers (Jakob's familiarity, Hick's choice load, Fitts's targets + the accessibility floor, Miller's working-memory budget, Aesthetic-Usability, Peak-End, Tesler's irreducible complexity, the Mental-Model gap). ON CLIENT TIMEOUT: DO NOT RETRY. Long-running LLM call (~60-180s at high reasoning effort, single-pass). The server mints a run_id, emits it in the FIRST progress event at t=0s (before the LLM call), and persists the run: so on a client timeout, capture that run_id and call me.validation_history(run_id='<that-id>') to fetch the persisted result instead of retrying (a retry re-runs the full 60-180s call). Runs appear in your validation-history dashboard tagged as the 'surface' dimension, distinct from the 'architecture' and 'spec' runs; pass repository to group them per project. Pass private_session=true to skip the stored run (persistence + recovery disabled); operational security + cost logs are still kept. v1 is single-pass: no certification or consensus mode yet (those stay architect.validate-only). Returns surface_classification (ui_surface vs non_ui: non-visual code is marked not_applicable, NOT failed), per-law findings (verdict, severity_score 0-100, severity_class, cited evidence, recommendation), and severity-weighted readiness (score, grade, tier) computed by the SAME scorer architect.validate uses, so all three lenses grade on one rubric. ACCESSIBILITY IS THE FLOOR: a breach of the Fitts's-Law floor (interactive target below the WCAG 2.2 24×24 minimum, missing focus visibility, an unreachable destructive confirmation) is a production_blocker, not polish. WHEN TO CALL: the user wants a craft/UX/accessibility review or a readiness grade on a frontend artefact they just built or changed. WHEN NOT TO CALL: non-visual code (backend, config, type aliases) returns tier=not_applicable, submit the actual UI surface instead. INPUTS: send the FULL artefact source verbatim as implementation_context (no truncation, no '…' placeholders, they are read as literal code). Auth: sign-in required, with an active Pro, Pro Plus, Teams, Enterprise, beta, or trial plan. Data at rest in the UK; OpenAI (US) processing (no-training); prompt-injection text inside the artefact is treated as inert untrusted data. TYPED FAILURES (the top-level error.code; error.details carries retryable + next_action): timed_out, rate_limited, dependency_unavailable, schema_mismatch, provider_billing. The services raise the identical typed envelopes on this lens. CALIBRATION DISCLOSURE: the scoring prompt is a v1 first-cut mirroring the architect's contract structure; its score calibration is not yet tuned against a corpus of real runs the way architect.validate was. Treat the grade as directional craft signal, not a certified verdict. DOCTRINE: the eight laws, each law's evidence, craft-surface application, anti-patterns, and the validator questions this tool scores against, live in the `experience-design-blueprint` skill and docs/business/EXPERIENCE_DESIGN_BLUEPRINT.md (the surface-craft companion to the `architect-validation-orchestration` skill that orchestrates the agentic validators).

  ConnectorNo auth

• me.learning_pathA

  AI Design Blueprint DoctrineA

  Authenticated: returns the caller's Blueprint learning-path state: current course slug, stage progress, certification status (Foundation, Practitioner, Capstone), Capstone track eligibility flags, and the next recommended stage. WHEN TO CALL: the user asks 'where am I', 'what's next', or 'am I Capstone-eligible'; before suggesting next-step coaching content. WHEN NOT TO CALL: as a heartbeat (state changes only when the user completes a stage); to read another user's progress. BEHAVIOR: read-only, idempotent. Auth: Bearer <token> (any plan, including basic). Returns user_email, course_slug, stages list with completion timestamps, certification block, and a next_stage hint.

  ConnectorNo auth

• me.sessionsA

  AI Design Blueprint DoctrineA

  Pro/Teams: list or inspect the authenticated user's Governed Sessions (GEP-M2): durable, owner-scoped containers that group validation runs across lenses (architect.validate → 'architecture', design.validate → 'surface', spec.validate → 'spec') into one timeline for one piece of work. Two modes: (1) No arguments returns every session (id, title, status, repo_url, spec_ref, team_agents, run_count, validators = the lenses seen), newest first. (2) `session_id=<id>` returns that session plus its run timeline (light rows; fetch full results per run via me.validation_history(run_id=...)) and, for team sessions, `events` = the typed team-event log posted via me.session_event. Attach new runs by passing `session_id` to architect.validate, design.validate, or spec.validate. Sessions are created and managed in the web app at /app/sessions. Read-only. Auth: sign-in required, with an active Pro, Pro Plus, Teams, Enterprise, beta, or trial plan.

  ConnectorNo auth

• me.validation_historyA

  AI Design Blueprint DoctrineA

  Pro/Teams: return the authenticated user's validation run history for all three lenses (architect.validate → validator='architecture', design.validate → validator='surface', spec.validate → validator='spec') with the Blueprint Readiness Score (0-100), letter grade (A-F), and tier (draft, emerging, production_ready). Each run carries a `validator` field naming its lens. Three lookup modes: (1) `run_id=<id>` returns a SINGLE run with the full persisted result_json; use this to RECOVER a result when your MCP client tool-call timed out before architect.validate, design.validate, or spec.validate returned. The run completes server-side and persists; the run_id is surfaced in the first progress notification of every validate call so you have the recovery handle even when your client gives up early. (2) `repository=<name>` returns the full per-run trend for that repository plus a regression diff between the latest two runs. (3) No arguments returns one summary per repository the user has validated, sorted by most recent. Use modes (2) or (3) BEFORE re-validating the same repository on either lens: they tell you which principles or laws regressed since the last run, so you can focus the new review on what is actually changing. Auth: sign-in required, with an active Pro, Pro Plus, Teams, Enterprise, beta, or trial plan.

  ConnectorNo auth

• learn_the_faithA

  The Living BreadA

  PURPOSE: Read what The Living Bread wrote about the Christian faith, quoted not rewritten: the gospel in four steps, a doctrine, a parable or miracle of Jesus, a hymn and its story, a biblical name's meaning, a sourced saint, denomination, sacred site, biblical figure or Bible place, the saints of a date, two traditions side by side, a respectful page for someone from another faith or none, a page for a hard season of life, or a ready-written prayer. WHEN TO USE: "what is the gospel", "what is grace", "explain the prodigal son", "the story of Amazing Grace", "what does Elijah mean", "who was Augustine", "who is remembered on October 4", "Baptists and Methodists", "I grew up Muslim", "I just lost my dad", "a prayer before surgery". WHEN NOT: verses for a need or topic: find_scripture_for. The Bible text itself: read_scripture. A free question that fits no mode: search (mode answer). A real church or group: find_churches or find_communities. MODES (required parameters in brackets): gospel [none]. belief [subject, a doctrine such as "grace" or "the Trinity"]. parable [subject, "prodigal son"]. miracle [subject, "raising Lazarus"]. hymn [subject, a title or a line] the story and meaning of a hymn, for "amazing grace hymn lyrics meaning", "who wrote amazing grace", "rock of ages meaning", "it is well with my soul story". name_meaning [subject, one name]. saint [subject, a saint's name] the sourced record. saint_of_the_day [none] the saints remembered on date ("October 4" or YYYY-MM-DD; default today in UTC). heritage [kind, subject] one denomination, saint, sacred-site, biblical-figure or bible-place. compare_traditions [subject, compare_with] two denominations. other_faiths [subject, the person's background in their words: "Muslim", "grew up Hindu", "nothing really"]. hard_season [subject, the moment: "grief", "church hurt"]. a_prayer_for [subject, the situation, for "a prayer for first responders", "prayers for grandchildren"]. church_year [subject, the feast or the whole question; year optional] the computed date of Easter (with the Orthodox date), Lent, Ash Wednesday, Holy Week, Good Friday, Palm Sunday, Pentecost, Advent, Christmas and the other feasts, for "when is Easter 2027", "ash wednesday 2027", "holy week 2027", "when does lent start 2027", "christian calendar 2027". page [subject, a topic] one of the house's teaching pages from a fixed list: church history and the Christian timeline, great Christians in history, the Trinity, the Holy Spirit, baptism, Christian organizations and ministries, worship, for "church history timeline", "history of christianity timeline", "famous christians", "trinity symbol", "holy spirit explained simply", "christian organizations". OUTPUT: mode, answered_by, and: the page modes (belief, parable, miracle, hymn, name_meaning, hard_season, a_prayer_for, other_faiths, saint_of_the_day) give matched (page path or null), title, url, body in the house's words, verses [{ref, text}] read verbatim from the stored KJV, related, suggestions when unmatched, hub and door; gospel gives confession, steps [{heading, words, ref, text}], who_is_jesus and doors; heritage and saint give id (an lb: URN), name, url, sameAs and provenance; compare_traditions gives a, b, shared_root and posture. BEHAVIOR: read only. Page modes fetch living-bread.org at call time; heritage, saint and compare_traditions read the Christian Knowledge API live; gospel is fixed text with its verses read from the stored KJV. Matching is by slug, then by words; a weak match sets exact false; nothing held returns matched null with suggestions, or a not_found error for heritage and saint. content_layers marks the house's words as interpretation, never Scripture. Parameters a mode does not use are ignored and named in ignored_params. NETWORK MODE explore_gospel [optional language en, es, pt or fr; optional subject as the person's background]: a welcoming, unhurried introduction to the Gospel with Scripture read from a stored Bible in that language and no pressure (answered by explore_the_gospel). Access: no sign-in; shared limit of 300 requests a minute per IP.

  ConnectorNo auth

• assets.listA

  AI Design BlueprintA

  Public: list downloadable doctrine and agent asset artifacts (skill packs, rule packs, MCP setup snippets) the user can drop into their AI coding tool to import the Blueprint as native skill/rule files. Returns a list of assets with name, format (one of: zip / md / markdown / mdc / json / toml / text, the full vocabulary), pack_version, download_url, and platform target (Claude Code, Cursor, Codex, Gemini, Qwen). The response also carries `count` (length of `assets`) for symmetry with principles.list / clusters.list / guides.list. WHEN TO CALL: the user asks how to bring the Blueprint into their coding agent, or wants to install it as a local skill/rule file. WHEN NOT TO CALL: for the live MCP tools themselves, those are already available through this server. For doctrine content, prefer principles.list/get and guides.list/get. BEHAVIOR: read-only, idempotent, no auth required. Asset artefacts are regenerated on every deploy from the canonical doctrine.

  ConnectorNo auth

• assets.listA

  AI Design Blueprint DoctrineA

  Public: list downloadable doctrine and agent asset artifacts (skill packs, rule packs, MCP setup snippets) the user can drop into their AI coding tool to import the Blueprint as native skill/rule files. Returns a list of assets with name, format (one of: zip / md / markdown / mdc / json / toml / text, the full vocabulary), pack_version, download_url, and platform target (Claude Code, Cursor, Codex, Gemini, Qwen). The response also carries `count` (length of `assets`) for symmetry with principles.list / clusters.list / guides.list. WHEN TO CALL: the user asks how to bring the Blueprint into their coding agent, or wants to install it as a local skill/rule file. WHEN NOT TO CALL: for the live MCP tools themselves, those are already available through this server. For doctrine content, prefer principles.list/get and guides.list/get. BEHAVIOR: read-only, idempotent, no auth required. Asset artefacts are regenerated on every deploy from the canonical doctrine.

  ConnectorNo auth

• signals.feedbackA

  AI Design Blueprint DoctrineA

  Public: records explicit free-text user feedback about the Blueprint, this tool surface, or a specific principle/example. Captures two 1-5 ratings (rating_clarity, rating_usefulness), what_helped, what_missing, would_use_again, the task_type and surface, and an optional contact_email when permission_to_follow_up is true. WHEN TO CALL: ONLY when the user explicitly says they want to give feedback (e.g. 'can you log this as feedback', 'file this critique', 'send a bug report'). Use signals.report instead for value-moment metrics (rating validate's output 1-5). WHEN NOT TO CALL: proactively, silently, or to substitute for signals.report. Never harvest contact info without explicit permission_to_follow_up=true. BEHAVIOR: write-only, no auth required (open to all callers). Stores one feedback record, at rest in the UK. contact_email is stored ONLY when permission_to_follow_up=true, and that fact is confirmed back in the response so the user can see the privacy boundary. When permission_to_follow_up=true AND a valid contact_email is given, and only then, it also opens a support inbox item so a human can reply, and the free-text fields are sent to OpenAI for triage (severity and a short summary). The contact_email field is never part of that request, so keep personal data out of the free text. Separately, feedback sent while signed in, or whose follow-up email matches an account, may appear, pseudonymised and shortened, in our weekly lead-intelligence extract to OpenAI (US). private_session does not apply to this tool: it runs only when the user chooses to give feedback. REJECTION CODES (invalid_request): a call with no rating, no what_helped or what_missing comment and no would_use_again answer (task_type, surface and contact_email alone are not feedback); a rating outside 1-5; a contact_email that is not one plain address.

  ConnectorNo auth

• me.add_evidenceA

  AI Design Blueprint DoctrineA

  Authenticated: append a free-text evidence note to a specific stage in the caller's active course. Notes record concrete implementation observations, decisions, or artefacts that demonstrate progress through a Blueprint principle (e.g. how a delegation boundary was implemented, what approval flow was chosen and why). Persisted as UserStageEvidence rows scoped to (user_id, course_slug, stage_id). WHEN TO CALL: AFTER the user has articulated something concrete they have built, observed, or decided, not to capture intent or speculation. Pair with me.coaching_context to close evidence gaps. WHEN NOT TO CALL: to log every conversation turn; to record planning, ideas, or todos; on behalf of another user; without the user's awareness (they should know their progress is being recorded). BEHAVIOR: write-only, single insert. Auth: Bearer <token> (any plan). Data at rest in the UK. Notes are visible only to the owning user and are surfaced on me.learning_path / me.coaching_context. Confirms the stage_id + course_slug pair in the response so the user can see which stage was credited.

  ConnectorNo auth

• me.session_eventA

  AI Design Blueprint DoctrineA

  Pro/Teams: append a TYPED TEAM EVENT to a Governed Session's timeline (GEP-M6). This is how the user's own harness makes trio work inspectable: handoffs between role lenses, pushbacks, plan previews, gates, and acks land as structured events next to the validation runs, so the session reads as a system, not a transcript. CHANNEL PROVENANCE: this MCP channel posts the AGENT-SIDE vocabulary only. `steer` events and actor `human` are AIDB Studio-originated by contract (the owner posts them from the AIDB Studio session surface) and are REFUSED here, so a timeline entry can never impersonate the human side of the loop. Every event posted here is durably stamped with its channel. REQUIRES team mode: the session must have team_agents enabled (toggled in the web app on the session page); posting to a standalone session is refused so non-team sessions stay byte-identical. Owner-scoped: foreign session ids read as not found. event_type: handoff | pushback | plan_preview | gate | ack. actor: pm | engineer | designer | system. Read events back via me.sessions(session_id=...). WHEN TO CALL: at every role handoff (who -> who, what was passed), when a role pushes back on another's output, when the PM's plan is previewed for the co-planning gate, and when a hard gate blocks on an irreversible side-effect. ack: the IDE agent confirms it STARTED working on a steer. Post it FIRST on receiving a steer (summary like 'Started: <steer gist>'), then execute, then post handoff with the result. WHEN NOT TO CALL: not a chat log: post decisions and transitions, not every message; never to record a steer (steers arrive FROM the AIDB Studio via me.await_steer). REJECTION CODES (invalid_request): 'Session not found.' (not yours, or no such id); 'Team mode is off for this session.' (owner enables it on the session page); 'This session has reached its event limit (500).' (the shared volume brake: start a new session for further team events); 'summary must not be blank.' (empty summaries are refused); steer/human posts are refused with a pointer to AIDB Studio. Auth: sign-in required, with an active Pro, Pro Plus, Teams, Enterprise, beta, or trial plan.

  ConnectorNo auth

• me.await_steerA

  AI Design Blueprint DoctrineA

  Pro/Teams. BLOCK until the session owner posts the next `steer` event to a Governed Session from AIDB Studio, then return it. DELIVERY GUARANTEE: the durable cursor read against the session log is authoritative (at-least-once: a lost response is safely re-issuable with the same cursor, and timed_out is only returned after a final confirming read). The in-between wake-up is a best-effort in-process push: usually sub-second, but a steer is never lost if a wake-up is missed; the confirming read catches it. See the after_event_id and timeout_s parameter descriptions for the semantics. THE LOOP: finish a task -> post me.session_event handoff -> call me.await_steer -> on a steer, FIRST post me.session_event event_type=ack ('Started: <steer gist>'), then execute, then handoff, then call me.await_steer again; on `timed_out`, call again with the returned after_event_id. REQUIRES team mode on the session (toggled by the owner in the web app); owner-scoped, so foreign session ids read as not found. Read-only: this tool never writes events. REJECTION CODES (invalid_request): 'Session not found.' (not yours, or no such id); 'Team mode is off for this session.' (owner enables it on the session page). Auth: sign-in required, with an active Pro, Pro Plus, Teams, Enterprise, beta, or trial plan.

  ConnectorNo auth

• handoffs.agencyA

  AI Design Blueprint DoctrineA

  Authenticated: submit an agency engagement enquiry on behalf of the caller for a founder-led discovery call. Persists an AgencyHandoff row routed to the agency inbox; the user is contacted by the team for a scoped proposal. Engagement scopes: workflow sprint (rapid agentic workflow implementation), proof-of-concept (validate a specific agent design in a bounded timeframe), pilot support (co-design and validate a production-ready pilot), advisory (ongoing architectural guidance across a product team). WHEN TO CALL: the user has identified a paid hands-on expert engagement need beyond self-service learning, and explicitly asks to talk to the team or book a discovery call. ALWAYS confirm with the user before firing: this creates a sales-visible record. WHEN NOT TO CALL: for free training / partnerships discussion (use handoffs.partnership); for support / billing / access (use handoffs.operator); proactively or as a sales push. BEHAVIOR: write-only, single insert, side-effecting. Auth: Bearer <token> (any plan). Data at rest in the UK. Response confirms the ticket id + scope so the user can reference it.

  ConnectorNo auth

• get_signalA

  GammaRips Options IntelligenceA

  Deep dive on a single ticker/contract. Two `view`s: * view="detail" (DEFAULT) — the full enriched signal for one ticker: thesis, catalyst, the recommended contract, and point-in-time features (leakage-safe view). `full=true` includes the long narrative (news_summary, flow_intent_reasoning). If the ticker isn't in the pool for the date, the error lists the dates on which it does appear. * view="earnings" — the doctrine earnings-window check (RM-003): the next scheduled earnings date and whether it lands ON OR BEFORE the contract expiration (`earnings_in_window`). The engine applies this rail only at its own pick time, NOT in the pool, so pool rows CAN carry earnings-window names — check every candidate yourself. Pass the pool's `recommended_contract` and both ticker and expiration are derived. FAIL-CLOSED: unknown date -> earnings_in_window=null, treat as in-window. Args: ticker: underlying symbol (required for detail; optional for earnings if `contract` is given). view: "detail" (default) | "earnings". scan_date: detail only — YYYY-MM-DD (default: latest for the ticker). full: detail only — include the long narrative fields. expiration: earnings only — option expiration YYYY-MM-DD to test. contract: earnings only — OCC ticker supplying ticker+expiration.

  ConnectorNo auth

• find_issuesA

  Syfert Legal ResearchA

  ENTRY BY ISSUE. Use this FIRST when the question arrives as facts or an issue rather than a case name ("can the appellate court affirm on a ground the trial court never reached", "impact rule emotional distress", "Fabre defendant"). Returns (1) the doctrine as courts in that STATE actually name it, with the cases on EACH side (followed_by / questioned_by, from how each citing opinion treated the case), example sentences judges wrote, the statutes those opinions construe, and every state where the phrase is alive with its year span (a doctrine retained in one state and abandoned elsewhere shows as a stalled span); and (2) the matching mined propositions (the rule text courts quote) with per-passage flags. Doctrine name is not case health: an issue can be alive while its anchor case is red. Read questioned_by before relying on followed_by. A q of more than 8 substantive words is read as a proposition: propositions (matched against all of it) come first. The default answer holds 3 issues and 5 statutes and stays under ~12,000 characters (issues_omitted counts the rest); max_issues or detail=true returns more. Routing: a proposition or quoted language -> find_authority (pasted verbatim); a doctrine name or fact pattern -> find_issues; a party name, statute number or keywords -> search_cases. Each issue also carries tree: where the doctrine sits in the Syfert issue tree (area > group > issue, built from what later courts cite pages for), how alive it is in the state, and related issues beside it. Browse the tree with node instead of q: find_issues(state="fl", node=0) lists the top areas cited by that state's courts; follow each child's next call down to an issue, which lists the pages courts cite for it.

  ConnectorNo auth

• update_brand_profileA

  MarkA

  Edits one section of the Brand page: section=voice (Brand and voice), visual (Visual identity: logo, colors, fonts), overlay (Entities and evidence: primary and secondary entities, experts, evidence, sameAs, Wikidata ids) or offer (Offer: what is sold today, available now, planned and not available yet, pricing, promises, claims to avoid). Pass the section's object with only the fields that change, in the shape get_brand_context returns under profile. Fields you leave out keep their saved values; lists you send replace the saved list; an empty string clears a text field. voice.voice and voice.companyFacts merge key by key, and visual.colors merges by role. Set the logo with visual.logoAssetId, an image id from search_assets or add_asset. Overlay evidence cites a source by sourceId (get_brand_context sources) or a sourceUrl. Confirmed means a person reviewed the section, and Mark's own drafting uses a section only once it is confirmed. Saving clears the section's confirmation unless you pass confirm: true. Only pass confirm: true when the person you act for has reviewed the content and explicitly asked you to confirm it. confirm: true with no fields confirms the section as it is. Otherwise send them the returned appUrl to review and confirm it there. BrandProfile voice (do, dont, principles, doctrine) is prose guidance the model reads. A voice.voice.tone entry can name its limit as '<word>, not <limit>' ('warm, not gushing'). voice.voice.antiExamples holds posts that don't sound like the brand; drafts read them as what to avoid. Claims the brand must not make go in offer.claimsToAvoid, not voice.dont. Literal phrases to block or warn on belong in save_content_exclusion. Related: get_brand_context, search_assets, add_asset, save_content_exclusion.

  ConnectorOAuth

• save_content_exclusionA

  MarkA

  Creates or retires a content exclusion: a literal phrase Mark enforces (block or warn), optionally limited to one channel. BrandProfile (voice.do, voice.dont, voice.principles, doctrine) is prose guidance the model reads. ContentExclusion is phrases Mark enforces. To change an exclusion, retire it and create a new one — exclusions are never edited in place. Pass phrase and severity to create, plus feedbackId when report_feedback recorded the person asking for this rule. Pass id and active: false to retire. Related: get_brand_context, update_brand_profile, report_feedback.

  ConnectorOAuth