"Arc" matching MCP tools:

• architect.validate

  AI Design Blueprint

  Pro/Teams — first-pass doctrine review of agentic code/workflow against the 10-principle Agentic AI Blueprint. 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 20-minute budget. Edge case: if the transport dropped 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. 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 20 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: Bearer <token>, Pro/Teams plan. UK/EU residency; transient OpenAI 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. 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: timed_out, rate_limited, dependency_unavailable, schema_mismatch (each carries retryable + next_action). 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.

  Connector

• architect.validate_consensus

  AI Design Blueprint

  Pro/Teams — N-shot CONSENSUS doctrine review of agentic code. ON CLIENT TIMEOUT — DO NOT RETRY THIS TOOL. Long-running (~80-120s for N=3 parallel LLM calls); MCP clients often close the call before the server returns. Retrying re-runs N × 60-180s LLM calls from scratch and burns N× compute. RECOVERY: same heartbeat pattern as architect.validate — the run_id is emitted in the FIRST progress event at t=0s (before LLM children fire); on timeout, call `me.validation_history(run_id='<that-id>')` to fetch the persisted consensus envelope. Runs N parallel `architect.validate` calls with private_session=True, then aggregates them to a per-principle MODE verdict + median severity + per-principle stability + score range/stdev. Returns one ConsensusValidationResponse with the headline median score, the honest variance band, and a representative full ValidationResponse (the child whose score is closest to the median). WHEN TO CALL: the user wants an HONEST first-pass score on agentic code, with the architect's variance surfaced. The single-shot `architect.validate` re-asserts the prior persisted run's verdict via baseline-anchor injection — same code can score 60/C anchored vs 98/A unanchored. Consensus mode is the unanchored honest read. WHEN NOT TO CALL: when you NEED the iteration delta against a prior run (regressions/improvements panel) — for that, call `architect.validate` which keeps baseline injection on. CHAIN RESUME: each child runs with `private_session=True` (no anchor) on purpose, but the CONSOLIDATED outer row IS persisted with `lifecycle_status='completed'` — the next single-shot `architect.validate` on the same repository auto-resolves it as prior_run_baseline. Consensus checkpoint becomes the new anchor. See the `architect-validation-orchestration` skill in the agent-asset pack for the full validate → consensus → certify sequence. BEHAVIOR: N (default 3, max 5) parallel LLM calls run concurrently; wallclock ~80-120s for N=3 (max child latency, not sum). Cost = N × LLM bill. Each child runs with private_session=True so the doctrine prompt's prior-run baseline injection is suppressed (no anchor bias). One CONSOLIDATED `UserValidationRun` row is written carrying the consensus envelope; the N children themselves do NOT persist (private_session contract). AUTH: Bearer <token>, Pro/Teams plan. Same paid-plan gate as architect.validate. INPUTS: same shape as architect.validate. `n` is the only extra arg (range 2..5). `private_session` is implicit (always true for children); the OUTER consolidated row IS persisted unless the tool itself is called inside another private context — but no such wrapper exists today. OUTPUT: response carries `score_consensus_median` (headline), `score_stdev` (honest uncertainty), `score_range` (min, max), `mode_stability_min_pct` (the cert-eligibility gate's input — ≥ 80% means the consensus is stable), `per_principle` (mode + distribution + severity median per principle), and `representative_response` (the closest-to-median child's full ValidationResponse so existing UI components render unchanged). TYPED FAILURES: same as architect.validate (timed_out, rate_limited, dependency_unavailable). Plus consensus-specific: `consensus_quorum_failed` when fewer than 2 child runs succeeded (≥ 2 required to compute a meaningful median).

  Connector

• architect.certify

  AI Design Blueprint

  Pro/Teams — second-pass adversarial certification of an architect.validate run that scored production_ready (A or B first-pass tier). ON CLIENT TIMEOUT — DO NOT RETRY THIS TOOL. **RECOVERY FIRST**: 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 cert verdict; the server-side run completes independently within a 20-minute budget. This is the canonical recovery path. Use it before considering any retry. Long-running LLM call (60-180s typical; exceeds Claude Code's ~60s idle budget); MCP clients commonly close the call before the server returns. Retrying re-runs the LLM call AND burns one of your 3 cert retry-budget attempts. Mints the certified production_ready badge when both reviewers sign off; caps the run to C/emerging when the second pass surfaces a missed production_blocker. MANDATORY DOCTRINE RULE (load-bearing): the badge certifies the EXACT code that produced the validate run_id, NOT 'this codebase' in general. If you modify, fix, or iterate the code between architect.validate and architect.certify — even a single character — cert rejects with code_fingerprint_mismatch. Fixing the code voids the run. The recovery path is always: edit code → architect.validate → fresh run_id → architect.certify on the fresh run. Do NOT cert from a stale run_id after iteration; ask the user to re-validate first. WHEN TO CALL: only after architect.validate returned tier=production_ready AND the user wants the certified badge AND the code has not been touched since the validate run. NOT for tier=draft/emerging/not_applicable runs (typed rejections fire — see below). NOT idempotent across attempts: each call is one of the 3 attempts in the retry budget. BEHAVIOR: atomic one-shot single LLM call, ~60-180s server-side at high reasoning effort (small payloads finish faster; observed p99 ~250s; server-side budget is 20 min, ~5× observed max). Exceeds typical MCP-client tool-call idle budget (~60s in Claude Code), so the FIRST notifications/progress event fires at t=0 carrying the run_id. The run is atomic by contract — no in_progress lifecycle, no cancellation, no resume. Updates the persisted run's result_json (public review URL + me.validation_history(run_id=...) reflect the cert outcome). ELIGIBILITY GATE (typed rejection enum on failure): caller must own the run, tier=production_ready, less than 24h old, not already certified, within cert retry budget (max 3 attempts), no other cert call in flight for the same run_id, code fingerprint must match the validated code, AND the submitted payload must be cert-payload-complete (see Payload Completeness below — cert rejects pre-LLM with `payload_incomplete` when an imported module's surface isn't visible in the validate payload that produced this run_id). Rejection reasons (typed Literal): auth_required, paid_plan_required, run_not_found, not_run_owner, not_eligible_tier, not_agentic_component (tier=not_applicable runs), already_certified, certification_age_exceeded, retry_budget_exhausted, code_fingerprint_mismatch, code_fingerprint_missing, code_not_on_file (caller omitted `code` argument AND the 24h cert-retry hold for this run has expired or was never written. Recovery: re-run architect.certify from the same MCP session that ran architect.validate, passing the code explicitly — the server never persists code by design), payload_incomplete (submitted/validated payload imports modules whose contents aren't visible — cert refuses pre-LLM to prevent a false-precision downgrade. Recovery: re-validate with verbatim public-surface stubs for every imported module, then re-cert on the fresh run_id. Empirically validated: PR #157 iter8/iter9 cert rejections were exactly this class — code on disk was correct, the submitted payload merely omitted module visibility), cert_consensus_score_below_threshold (consensus_median<75 — consensus runs only), cert_consensus_unstable_blocker (any principle mode_stability<80% — consensus runs only), run_state_corrupt, cert_persistence_failed, cert_in_flight (a prior architect.certify call on this run_id is still running. Poll me.validation_history for the verdict; do not retry until it resolves). PAYLOAD COMPLETENESS (load-bearing for cert eligibility): the cert reviewer reads the EXACT payload that produced the validate run_id. Imported modules whose surface isn't present in the payload cause pre-LLM `payload_incomplete` refusal. Avoidance — when validating with intent to cert, bundle 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 you reference; module-level imports of `dataclass`, `Literal`, `json`, `datetime`, `timezone` MUST also be in the payload (cert correctly catches when they're omitted — code would NameError on import). 'Submit Like Production': the payload should be the code as it would actually run, not a compressed sketch. The stubs cover IMPORTED dependencies only; the certified code's own enforcement branches (approval gates, policy checks, recovery paths) must be present in full. A `# ...` placeholder reads as an ABSENT control and is graded against you, not as shorthand for one that exists. PRE-LLM REJECTION AUDIT TRAIL: when cert rejects before the LLM call (payload_incomplete, code_fingerprint_mismatch, etc.), `certification_attempts=[]` on the response — no attempt landed in the retry budget, no LLM hop occurred. The rejection envelope's `rejection_reason` + `guidance` are the actionable surface. (Audit-trail UI surfacing of pre-LLM rejections is tracked in the platform self-audit set as anomaly #5; out of scope for the cert tool itself.) INPUTS: re-send the SAME code that produced the run_id (the architect persists findings + recommendations, never code, by design — privacy-preserving). Server compares the submitted code's SHA-256 fingerprint to the stored fingerprint and rejects mismatches. Auth: Bearer <token>, Pro or Teams plan required. UK/EU data residency (Cloud Run europe-west2). Code processed transiently by OpenAI (no-training-on-API-data) and dropped; payloads JSON-escaped + delimited as inert untrusted data — prompt-injection inside code is ignored. If the cert call fails outright (provider error, persistence error), a fresh architect.certify is the recovery path; the eligibility gate enforces the 3-attempt retry budget. For long-running cert workflows the answer is to re-validate, not to make this tool stateful. OUTCOMES: certification_status ∈ {confirmed_production_ready (badge mints), downgraded_to_emerging (cert review surfaced a missed production_blocker, tier capped at C/emerging), unavailable_provider_error (LLM call failed, retry within budget)}. Cert findings + summary + attempt history surfaced on the persisted run for full inspectability.

  Connector

• get_experience_prompt

  Matthew Hartley Music MCP

  Returns the curated Claude prompt, intro hint, pairing hint, arc role, and experience recipes for a song. Use this to get first-class directives for how to present a song rather than interpreting raw metadata.

  Connector

• generate_video

  Hermoso

  Render a RAW video clip from your own prompt and return its served mp4 URL. For finished brand ADS prefer render_ad (it runs the Studio quality pipeline — composited text, clean speech, end card, music); use this for raw/experimental clips or precise manual control. ONE generation = one continuous clip up to the model’s longest listed duration (seedance-2 goes to 15s single-pass with a full multi-beat arc — never assume a generic 8–10s cap); durationSeconds must be one of the model’s durations from hermoso_capabilities. Renders take 1–3 min. refImage anchors the opening frame; ttsScript adds a voiceover. Pass refVideo (a clip URL) to EDIT an existing video instead of generating from scratch — the omni engine transforms that clip per your prompt, inheriting the source clip’s canvas + length (aspectRatio/durationSeconds are ignored for an edit). Spends credits (Starter plan is video-blocked server-side).

  Connector

• stitch_video

  Hermoso

  Render a multi-scene STITCHED video (≥2 scenes) — ONLY for spots LONGER than one model clip (>15s). A ≤15s multi-beat ad renders better and cheaper as ONE single-pass generate_video/render_ad on seedance-2 (it handles the full hook→demo→payoff arc in one take) — never stitch those. Blocks until done. Spends credits.

  Connector

• analyze_headers

  email-deliverability

  Re-verify SPF, DKIM, DMARC, and ARC from a raw RFC 5322 email (full message or just the headers block). Returns InboxGuard's independent verdict (`ours`), the sender's own Authentication-Results (`theirs`), whether they `agree`, and parsed envelope/headers — useful for spotting forged or mismatched auth results. No account needed.

  Connector

• browse_cards

  Art and Song Ecards

  Browse published ecards by category, keyword, and tags. Multi-word keywords or tags are split into individual terms for tag matching, so search concepts like sympathy and loss separately instead of relying on exact phrase tags.

  Connector

• get_card

  Art and Song Ecards

  Get one published ecard with pages, music options, fonts, and message placement.

  Connector

• create_ecard_draft

  Art and Song Ecards

  Create a pending single-card ecard draft for personalization. Do not collect recipient or purchaser email in MCP.

  Connector

• personalize_message

  Art and Song Ecards

  Set the salutation, message, footer/from line, and font for a pending ecard draft. Only set footer when the sender name is known from the prompt; if missing, ask for the From name before calling this tool. Recipient details are handled later on the website.

  Connector

• select_music

  Art and Song Ecards

  Select an audio track for a pending ecard draft. Call this before generate_preview whenever the chosen card has available music; choose the best matching track from the card's availableMusic list. Recipient details are handled later on the website.

  Connector

• generate_preview

  Art and Song Ecards

  Final MCP handoff step. Return preview data and a Personalise Your Ecard URL. Do not collect recipient email, discuss payment in MCP, or ask the user to type continue; show the previewUrl immediately so the user can review and complete the ecard on the website.

  Connector

• palette_gradient

  Colour Memory

  Generate a perceptually smooth gradient between 2-5 archive anchor colours. Each interpolated stop snaps to the nearest real archive colour by CIEDE2000. Anchor stops are kept true to their source. Choose linear (physically accurate Lab interpolation) or chroma_preserved (LCh interpolation, short-arc hue, avoids desaturated midpoints). Returns stop array, CSS linear-gradient string, or SVG swatch bar. Use for design briefs, colour journey visualisations, and gradient systems.

  Connector

• search_artists

  Provenio — Art Intelligence

  Cost: ~0.4s. Shortlist person nodes by name/nationality/era. Returns [{id, display_name, birth_year, death_year, nationality, era}]. Use when: you have a name but no person ID. Try a partial name if exact match fails (e.g. 'Basquiat' not 'Jean-Michel Basquiat'). Do NOT use if: you already know the ID — call get_artist directly (one call). Returns person IDs in 'person:slug' format — pass these directly as the 'artist' parameter in search_artworks. STOP after this unless you need a specific artist's full profile.

  Connector

• search_artworks

  Provenio — Art Intelligence

  Cost: ~0.5s. Shortlist artworks by title/artist/medium/date, or risk-filter (provenance_risk, attribution_status). Returns summary rows. Use when: you need a list, not one work's detail. Do NOT use if: you know the artwork ID — call get_artwork (one call contains iconography + custody + polity + transactions). Do NOT chain multiple search_artworks calls for the same work — use get_artwork after you have the ID. Do NOT put artist names in the query field alone — use the artist filter with the person ID slug (e.g. 'person:jean-michel-basquiat'). If title is ambiguous, combine query + artist filter. Title match is substring (ILIKE %query%). For best results, use the artist filter rather than embedding artist name in query. Note: when provenance_risk filter is used, returns coverage_gaps: ['no_custody_history'] when the matching custody record pool is smaller than expected — interpret this as a data-density limitation, not a clean result. STOP after this unless you need deep detail on ONE artwork.

  Connector

• search_auction_history

  Provenio — Art Intelligence

  Cost: ~0.7s. Auction transaction rows with optional percentile_summary=true to also return P25/50/75/90 + realized-vs-estimate in ONE call. Use when: need lot-level prices OR percentile stats. Do NOT use if: you only need per-artist aggregates — use query_market_summary. SINGLE-CALL FRIENDLY — combine filters + percentile_summary for appraisal work.

  Connector

• get_artist

  Provenio — Art Intelligence

  Cost: ~1s. Composite artist profile — identity + reception + 1-hop influence in/out + education + market aggregates. SINGLE CALL USUALLY SUFFICIENT. Use when: you have an artist ID and need their full picture. Do NOT chain with get_influence_network unless you need depth > 1. Do NOT use for multi-artist comparison — use query_market_summary.

  Connector

• get_artwork

  Provenio — Art Intelligence

  Cost: ~1s. Composite artwork profile — metadata + Panofsky subjects + reception + custody + polity + transactions. SINGLE CALL USUALLY SUFFICIENT. Use when: you have an artwork ID. Do NOT chain with get_provenance_chain unless you need gap-risk flags specifically.

  Connector

• get_movement_context

  Provenio — Art Intelligence

  Cost: ~0.5s. Concept node + linked artworks. Pass cross_tradition=true for hasFunctionalAnalog concepts (lotus↔rose). SINGLE CALL USUALLY SUFFICIENT. Use when: definitional context or iconography cluster. Do NOT use for artwork filters — use search_artworks.

  Connector