Tool search 101,866 tools · 5,225 live servers

Run a command or code in an open E2B sandbox session (started by `use` with action `create_session`, which returns a `session_id`). Pass `session_id` plus either `command` (a shell command) or `code` (+ optional `language`: python/javascript/bash). Returns stdout/stderr/exit_code (or the code result). The sandbox stays alive — and billed per second of uptime — until you `close` it; re-running reuses the SAME box, so filesystem + process state persist between calls. ALWAYS `close` when done.

Fetch a remote media URL (image/video/audio) and HOST it on Clipkit, returning a stable asset_url to put in an element's `url`. Use this so the project's media survives — the original link may rot, be private, or block hotlinking. Anonymous projects allow up to 5 hosted assets / 100 MB total / 50 MB per file; when the limit is hit, tell the user to open the project (open_in_editor) and sign in to add more. Requires project_id.

[Design Patent TRO risk control · WIPO global design / IP search] Query the WIPO design database across 12 sources (USPTO US designs, CNID China, HAGUE international registrations, …), with one-click chaining to US design-patent TRO (temporary restraining order) / litigation risk control. Use when: user says "check trademark" / "design patent search" / "any IP risk for new product" / "X company's patent portfolio" / "WIPO search" / "USPTO query" / "what is registration DM/XXX"; pre-launch IP clearance during scouting/GTM SOPs; competitor IP-portfolio research. Don't use: for keyword ranks / product reviews / product detail (this is an IP database, not a commerce database); for US text-trademark search (this DB focuses on design patents — text trademark coverage is limited). Returns: data.data.{ total, hits[{ IRN, HOL[], DETAIL_DATA.structured.{indication_of_products, statement_of_novelty, ...}, IMG[], IMG_DATA[{filename,url}], DC, RD, STATUS, LCS[], DS[], PROD[], SOURCE, DETAIL_URL }] }. With enableLitigation=true each matched patent additionally carries litigationStatus(success/skipped/failed) + caseTotal + cases[{ caseId, docketNumber, caseName, court, status, dateFiled, parties[], patentNumbers[], entries[] }] (backed by US PACER litigation data — one call returns patents + lawsuits). Pair with: ↑ source required; hol=holder name / prod=product name / irn=international registration / lcs=design classification; enableLitigation=true chains US litigation lookup (IP-risk loop, no separate tool needed); ↓ DETAIL_URL lets the user jump to WIPO's official page to verify. Cost: ~2 points/call, ~5s; with enableLitigation=true add +12 points only when a patent is found (free if none). ⚠️ Perf contract: CNID + hol/prod MUST be paired with id/idSearch/rd/status/lcs (otherwise the backend rejects to avoid a 17M-row full scan); JPID has no HOL/PROD; USID has no STATUS; ed (expiration date) is silently ignored on all sources — filter dates via rd instead. With enableLitigation on, each page re-triggers the litigation query and billing.

Convert a file from one format to another. Pass EITHER a publicly accessible URL (source_url) OR base64-encoded file contents (base64_content + source_format) — exactly one is required. Returns a temporary download URL (valid 1 hour; file deleted within 24 hours).

Translate a document into another language with the original layout and formatting preserved (DOCX, PPTX, XLSX, PDF, TXT, MD, SRT, VTT). The job runs immediately and returns a FREE preview of the first pages plus a secure Stripe checkout link — the full translated file unlocks after payment ($4.99, one-time, no account needed). Provide EITHER source_url OR base64_content, plus a filename with extension.

Extract every table from a PDF or image (PNG, JPG, WebP) into a clean multi-sheet Excel file. The job runs immediately and returns a FREE preview of the first table plus a secure Stripe checkout link — the full .xlsx unlocks after payment ($3.99, one-time, no account needed). Provide EITHER source_url OR base64_content, plus a filename with extension.

Compress a file (PDF, JPG, PNG, WebP, MP4, MOV, WebM) down to an exact target size — e.g. "under 5MB for an upload form". FREE (daily limit applies). Returns a download URL on success; if the target is physically unreachable it fails honestly and reports the smallest achievable size. Provide EITHER source_url OR base64_content, plus a filename with extension.

Describe what you want done to a file in plain language — e.g. "translate this contract to German", "pull every table out of this PDF into Excel", "shrink this video to under 25MB", "convert this to PDF". The instruction is routed to the right job automatically; if the request is not supported yet you get an honest explanation of what is. Provide EITHER source_url OR base64_content, plus a filename with extension.

Check the status of a previously submitted file job (translate_file, extract_tables, compress_file). Returns the current status, preview + checkout link for completed paid jobs, or the download URL for completed free/paid-and-unlocked jobs.

Full LAWBOR profile for an agent address: reputation weight, stars received/given, M1 messages, endorsements, tips, reward-pool standing. The one-call "who is this agent in the LAWBOR network" read.

Render an HTML string to a PDF using the headless-Chrome engine. Returns a { FileUrl } link (valid ~24h) by default. Great for invoices, reports, and letters produced as HTML. BILLED per document. Api2Pdf API: POST /chrome/pdf/html.

Fetch a web page by URL and render it to a PDF using headless Chrome. Returns a { FileUrl } (valid ~24h). Use extraHTTPHeaders to pass auth for a protected page. BILLED. Api2Pdf API: POST /chrome/pdf/url.

Render a Markdown string to a PDF using headless Chrome. Returns a { FileUrl } (valid ~24h). BILLED. Api2Pdf API: POST /chrome/pdf/markdown.

Render an HTML string to an image using headless Chrome. Returns a { FileUrl } (valid ~24h) by default, or base64 bytes with output_binary:true. BILLED. Api2Pdf API: POST /chrome/image/html.

Take a screenshot of a live web page by URL using headless Chrome. Returns a { FileUrl } (valid ~24h). BILLED. Api2Pdf API: POST /chrome/image/url.

Render an HTML string to a PDF using the wkhtmltopdf engine — an alternate to Chrome that supports a table of contents (pass enableToc / tocOptions inside `options`). Returns a { FileUrl } (valid ~24h). BILLED. Api2Pdf API: POST /wkhtml/pdf/html.

Use this when you need to resize an image from a URL or convert its format. Returns the resized image as base64 with metadata in JSON. Returns: 1. image (base64-encoded data) 2. originalWidth and originalHeight 3. newWidth and newHeight 4. format (png/jpeg/webp) 5. fileSizeBytes. Example output: {"image":"iVBORw0KGgo...","originalWidth":1920,"originalHeight":1080,"newWidth":800,"newHeight":450,"format":"webp","fileSizeBytes":24500} Use this FOR creating thumbnails, optimizing images for web, preparing social media images, resizing for email templates, and batch image processing. Do NOT use for OCR text extraction -- use media_extract_text_from_image instead. Do NOT use for QR code generation -- use utility_generate_qr_code instead. Do NOT use for screenshots -- use capture_screenshot instead.

ONE-CALL orientation before you build: pass `files` you're about to edit (or a `task`) → the systems that own them, each with Goal + Acceptance + build status/files/last_commit/drift + coupled_systems (code neighbors an edit may break) + pending Inbox changes + recent decisions, plus open-rejection count, who's active, `recent_changes` (what happened since you were last here — a session handoff), and a task to claim. Replaces the get_project_meta→get_system→get_build_region dance.

System→code map per built system: implementing files, status, drift flag, last_commit, and acceptance-evidence COUNTS. Mapped files gone from the repo? report_drift. Pass `system:"<name|id>"` for ONE system plus the full text of its acceptance criteria (omitted from the map — it is the bulk of the payload). Big projects come back paged: the body says 'page N of M', call again with `page: N+1`.

Flag CODE DRIFT — mapped files no longer match the repo. Advisory; a fresh report_build_status clears it.

BLAST RADIUS of a system (deterministic): upstream context, siblings, dependent screens/milestones, files, code-coupled systems, pending Inbox, recent activity. Run BEFORE changing it.

A screen's reference image (HUD background) as an actual IMAGE you can see — reads the stored file inline (signed-URL fallback past 4MB).

Report a SYSTEM's status (todo|in-progress|implemented) — DIRECT, live. ALWAYS pass files (full list — it REPLACES); non-todo with no files shows done-but-EMPTY. 'implemented' counts as VERIFIED only when every UNIT-TESTABLE ## Acceptance bullet is backed via evidence[{criterion,proof}]; a bullet tagged [manual]/[e2e]/[ui]/[wip] is EXEMPT (verified by manual/e2e). Otherwise it's a CLAIM (verified:false) and the response names the unbacked criteria. TWO tiers: VERIFIED = a test is NAMED; GREEN (guarantee) = you RAN the test and reported `passed:true` on the evidence — green goes stale after 21 days, so re-run to keep it.

How many photos or minutes of video actually fit in a given storage size, corrected for real OS/filesystem overhead. Backed by Cleanor Labs measured per-item sizes. Use for realistic sample copy, dashboards, or "how many photos fit in 128 GB" answers.

Turn a title or phrase into a clean, URL-safe slug (lowercase, hyphenated, accents stripped). Use when generating page paths, filenames or anchor IDs.

Submit a document (PDF or image) to a Mindee extraction model and return the structured fields. Provide EITHER document_url (a public URL) OR file_base64 (+ filename). This enqueues an inference and polls until it completes (up to ~30s); if it is still processing it returns a job_id you can poll with mindee_get_job then read with mindee_get_inference. NOTE: consumes Mindee API credits (paid, billed per page). V2 API: POST /v2/inferences/enqueue.

Transcribe audio or video to text, including per-word timestamps for precise editing. Three-call flow: (1) call with `filename` to receive {job_id, payment_challenge}; (2) pay via MPP, then call with `job_id` + `payment_credential` to receive {upload_url} (presigned PUT, 1h expiry); (3) PUT the bytes, then complete_upload(job_id), then poll get_job_status(job_id). On completion, get_job_status returns two outputs: role `transcript` (SRT) and role `transcript-words` (JSON matching /.well-known/weftly-transcript-v2.schema.json, with segment-level and per-word timestamps). For other formats, pass `format=srt|txt|vtt|json|words` to get_job_status to receive content inline — `txt` and `vtt` are derived from SRT, `json` is v1 (segments only), `words` is v2 (segments + words). Flat price: audio $0.50, video $1.00 — see /.well-known/mpp.json for the authoritative table. Use for podcasts, interviews, meetings, lectures, and especially for creating clips, multicamera edits, or edit-video-from-transcript where word boundaries matter. Retrying any call with `job_id` alone returns current state (idempotent). Failed jobs auto-refund.

Summarize an audio or video file — returns both a text summary AND the full transcript (with per-word timestamps). Do not also call transcribe on the same file. Three-call flow: (1) call with `filename` to receive {job_id, payment_challenge}; (2) pay via MPP, then call with `job_id` + `payment_credential` to receive {upload_url} (presigned PUT, 1h expiry); (3) PUT the bytes, then complete_upload(job_id), then poll get_job_status(job_id). On completion, get_job_status returns three outputs: role `summary` (plain text), role `transcript` (SRT), and role `transcript-words` (JSON matching /.well-known/weftly-transcript-v2.schema.json, with segment-level and per-word timestamps). For other formats, pass `format=srt|txt|vtt|json|words` to get_job_status to receive transcript content inline — `txt` and `vtt` are derived from SRT, `json` is v1 (segments only), `words` is v2 (segments + words). Flat price: audio $0.75, video $1.25 — see /.well-known/mpp.json for the authoritative table. Use for meetings, long-form interviews, lectures, and podcast episodes; the `words` output additionally supports creating clips, multicamera edits, or edit-video-from-transcript. Retrying any call with `job_id` alone returns current state (idempotent). Failed jobs auto-refund.

START HERE for any clip workflow on a video — `find_clips` is the canonical entry point and includes a full transcription as a free byproduct. **Do not call `transcribe` first**: doing so doubles the upload, doubles the spend, and produces the same transcript. Identify ranked candidate clips in a video — what to cut for highlights, social, or testimonials. Three-call flow: (1) call with `filename` (and optional `query`) to receive {job_id, payment_challenge}; (2) pay via MPP, then call with `job_id` + `payment_credential` to receive {upload_url} (presigned PUT, 1h expiry); (3) PUT the bytes, then complete_upload(job_id), then poll get_job_status(job_id). On completion, get_job_status returns three outputs: role `clip-candidates` (JSON matching /.well-known/weftly-clips-v1.schema.json — includes `source_job_id` and `source_expires_at`), role `transcript` (SRT, free byproduct), role `transcript-words` (JSON matching /.well-known/weftly-transcript-v2.schema.json, free byproduct). Each candidate carries `transcript_text` — the full text of what's in the clip — so callers can preview content before paying for extract_clip. Optional `query` parameter switches to query mode (e.g., "they discuss pricing", "the part about hiring") with the same output shape; the `mode` field in clip-candidates.json indicates which mode produced the result. Flat price: $2.00 video — see /.well-known/mpp.json. **Source-reuse contract:** the source video stays in storage for 72h after find_clips completes. Hand the find_clips `job_id` (also returned as `source_job_id` in the candidates JSON) to `extract_clip` or `extract_vertical_clip` as their `source_job_id` — within those 72h they cut directly from the stored source: no re-upload, no re-transcribe, just $0.50 per cut. Pass the same `source_job_id` to as many extract calls as you need. Use for interviews, podcasts, sales calls, all-hands recordings. Retrying with `job_id` alone returns current state. Failed jobs auto-refund.

Cut a 9:16 vertical clip from any prior video job (find_clips, summarize, or video transcribe), suitable for direct upload to TikTok, Instagram Reels, or YouTube Shorts. Default output is 1080×1920 H.264 / AAC `.mp4` with center-cropped framing; audio loudness-normalized to -14 LUFS / -1.5 dBTP for short-form social. Single-segment only; clip duration must be between 1 and 90 seconds (Instagram Reels max). Operates on a parent job — possessing the parent `source_job_id` is the capability, no upload step. Two-call flow: (1) call with `source_job_id` + `start` + `end` (in source seconds) to receive {job_id, payment_challenge}; (2) pay via MPP and call with `job_id` + `payment_credential` to start processing. Poll get_job_status(job_id) for completion; output is role `clip-vertical-video` (the `.mp4`). Flat price: $0.50 per clip. Payment: pay by credit card via the Stripe Checkout link (open the returned `payment_url` in any browser) or Tempo USDC via mppx. Optional `profile` parameter selects the encoding profile (default `tiktok-primary`). Allowed values: `tiktok-primary` (1080×1920, fast preset, CRF 22), `tiktok-primary-720p` (720×1280, CBR 3 Mbps — half-resolution mobile-optimized, ~40% faster wall time), `instagram-reels` (1080×1920, slow preset, CBR 4 Mbps), `instagram-stories` (same encode shape as instagram-reels). All four profiles loudness-normalize identically. Optional `subject` parameter controls reframing (default `center`, preserves today's behavior): `auto` locks onto the longest-tracked face from the parent's subjects-sidecar (or runs inline detection if the parent has none); `subject_id` (with `subject_id` param naming a face_N from the sidecar) locks onto a specific subject; `follow` switches crop between active speakers across the clip using the sidecar's active_speaker_timeline; `manual` accepts caller-supplied framing via `subject_box: {x, y, w, h}` (source pixels) or `subject_x_offset` (direct crop x). Sidecar shape at /.well-known/weftly-subjects-v1.schema.json. auto/subject_id/follow fall back to center if detection or sidecar resolution fails — the paid job always delivers a clip. Source must be a horizontal video (wider than 9:16) — already-vertical or square sources are rejected. Source must still be in storage (72h TTL for find_clips parents, 24h elsewhere — check `expires_at` from get_job_status on the parent). Pair with `find_clips` ($2.00/video) to pick a moment first, then call this to get a download-ready vertical mp4 in under 5 minutes. Multiple extract_vertical_clip calls against one parent are independent paid jobs. Failed jobs auto-refund.

Confirm that the file has been uploaded (via HTTP PUT to the upload_url from transcribe or summarize) and start processing. Verifies that the file is present in storage and that the job has been paid. Returns status "processing". Poll get_job_status to track progress and retrieve download URLs when done.

Check the status of a transcribe or summarize job. Returns the current state and, when completed, an `outputs` array. Each output has either `content` (returned inline) or a presigned, time-limited (1 hour) `download_url`. Small text outputs (e.g. `transcript` SRT, `clip-candidates`, `summary`) come inline as `content`; larger outputs — `transcript-words` JSON for any non-trivial recording, plus video outputs like `clip-video` / `clip-vertical-video` — come as a `download_url` to fetch when needed. Optionally pass `format` (srt, txt, vtt, json, words) to get the transcript content inline in the top-level `transcript` field — `txt` and `vtt` are derived from the stored SRT; `json` is v1 (segments only); `words` is v2 (segments + per-word timestamps matching /.well-known/weftly-transcript-v2.schema.json). Poll this periodically after calling complete_upload — wait at least 60 seconds between checks. For files under 10 minutes, jobs usually complete within 1-2 minutes. For long files (1hr+), expect 10-30 minutes. Also use this to recover from lost state: if the original challenge was lost, call get_job_status(job_id) to retrieve a fresh challenge (status "awaiting_payment") or the upload URL (status "awaiting_upload").

ACCOUNTING EXPORT: turn the verified receipts into an accountant-ready CSV that QuickBooks / Xero / Excel import (the export finance teams need to adopt). Every row carries its own txHash + Basescan link, so the accountant re-verifies each amount on Base themselves — the export is a POINTER to the chain, never a book to trust. Non-custodial (BIII moved no funds). Columns: date, receipt_no, reference, description, payer, gross_usdc, tip_usdc, charged_usdc, token, chain, tx_hash, basescan_url, status. Dedup by txHash; optional block-time window; brand slugs the filename.

IS A RECOVERY PHRASE SITTING IN CLEARTEXT ON THIS MACHINE? Everything else here answers whether an ADDRESS is safe to pay; this answers whether the MACHINE is safe to hold a wallet, and a safe address on a compromised machine is worth nothing. "Self custody if you know how to keep your seedphrase safe" puts the whole condition in the sentence and nothing ships that checks it: an antivirus answers "do you have a known virus", which is a different question. This one is DECIDABLE rather than scored. A keyword scan drowns — abandon, able, about and absent are ordinary English and all four are BIP-39 words — but a mnemonic is a RUN of 12/15/18/21/24 consecutive words from a 2048-word list with a CHECKSUM in the last word, so a candidate is proven by arithmetic. Measured across 204 files and 1.6 MB of real prose and source: zero false confirmations. It NEVER outputs the phrase — file, line and word count only, because this output ends up in terminal buffers, logs and screenshots, and a scanner that prints the seed it found is a stealer with good intentions. Reports its own blind spots: no images, PDFs, password managers, browser storage or encrypted archives, so "nothing found" means nothing was found IN WHAT WAS READ. Read-only, no network, nothing is copied.

WHAT KEY MATERIAL IS ON THIS DISK, AND WHAT STILL HOLDS AN OLD COPY OF IT? The companion to till_seed_exposure, and it exists because a real theft happened without the phrase ever being written down: the key was exfiltrated. The trap is that a secp256k1 private key is 64 hex characters and so is every SHA-256 hash, git object id and transaction hash in a saved response, so the value SHAPE carries almost no information. Two things do: STRUCTURE (a Web3 Secret Storage keystore has version 3 and a crypto member with ciphertext, kdf and mac — nothing else looks like that, and finding one is not an exposure but an encrypted wallet whose strength is its password) and THE LABEL (cleartext keys are named by what needs them, so PRIVATE_KEY matches and PRIVATE_KEY_HASH is rejected as a digest). RETAINED COPIES are what people miss: ROTATING A SECRET DOES NOT REMOVE IT FROM THE DISK, because editor history, session caches and backup folders keep snapshots of what the file used to say — on the machine this was built for, one .env holding three named keys had eighteen previous versions still readable, and the folder had been copied into a keep-across-the-reformat backup. Also reports browser wallet vaults by PRESENCE only, nothing opened or parsed, because that is how a key leaves a machine when it was never in a text file. Never outputs key material, not even a prefix: four bytes narrow a brute force. Never decrypts, never derives an address.

Validate a design token file against the W3C Design Tokens Community Group (DTCG) 2025.10 format, returning 10 conformance checks (t01-t10) with PASS/FAIL/WARN. Use this to verify a tokens.json (or any DTCG token export) is structurally correct — $type/$value/$description present, structured colors (colorSpace + components rather than bare hex), a valid $schema pointer to designtokens.org, and correct dimension units. Pass a URL to fetch the file, or a raw JSON string via dtcg_file. Executable — parses and validates server-side. Provenance: W3C DTCG 2025.10 CG-FINAL + designesy-core v0.3.0 §8. For scoring a whole live site (not just its tokens), use designesy_score.

Validate a Lottie animation file against the Lottie spec v1.0.1 and the Designesy §16 Ten Non-Negotiable Motion Standards, returning 10 checks (m01-m10) with PASS/FAIL/WARN. Use this to verify a motion/animation asset is well-formed and accessible — required fields (v, fr, ip, op, w, h, layers), $version, a markers array for reduced-motion, and no deprecated version. Pass a URL to fetch the Lottie JSON, or the raw JSON string via lottie_file. Executable — parses and validates server-side. Provenance: Lottie spec v1.0.1 + JSON Schema Draft 2020-12 + designesy-core v0.3.0 §7, §16. For a full-site motion/accessibility score, use designesy_score.

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.

Public — records explicit free-text user feedback about the Blueprint, this tool surface, or a specific principle/example. Captures category (bug, doctrine_critique, missing_example, ergonomics, other), free-text body, and 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), single insert into UserFeedback. UK/EU residency. 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.

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. 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 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.

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.

Return the Commonlands distortion model/status for one lens SKU, including whether the data is source-display-only or backend-calculated. Use this tool for FOV, HFOV, VFOV, DFOV, field of view, "lens for", lens-to-sensor, AR0234, IMX290, IMX477, and sensor part-number requests. It returns Commonlands data the model cannot derive: live backend FoV when configured, distortion model/status, image-circle coverage, live stock through Shopify read tools where applicable, and MTF/CRA/BFL fields if present in upstream catalog data. Do not use naive rectilinear fallback, focal-length-only math, interpolation, or self-computed catalog estimates when a Commonlands lens/sensor route is available. Use this for distortion, rectilinear-vs-wide-angle, MTF/CRA/BFL/optical-profile questions when upstream fields are present. Do not invent polynomial coefficients or claim measured distortion correction when the backend only returns display distortion.

Get upload instructions for media files (audio, images, video). Returns the upload URL and required headers. Requires API token authentication.

Search Deezer preview tracks by song, artist, or album. Use this when the user provides a song string but no MP3/WAV/FLAC file.

Create a compel from a selected Deezer preview track. If the user provides an audio file instead, upload that file and use create_compel.

Search and list uploaded media files for the authenticated account.

Get the exact price to analyze an audio file before committing. Always call this first. Returns cost in dollars and a job_estimate_id valid for 30 minutes. Free — never charged.

"Tell me about X" / "research Acme" / "brief me on Tesla" / "what does Apple do" / "company profile for Microsoft" / "give me the rundown on NVDA" / "everything you know about $TICKER" — full cross-source profile of a US public company in ONE parallel call. ALWAYS PREFER over chaining single-pack SEC/XBRL/news lookups when the user asks for a holistic view. Fans out across SEC EDGAR, XBRL, USPTO, news, GLEIF and returns: cik + company_name; recent_filings (up to 5 with pipeworx://edgar/company/{cik}/filings/{accession} URIs); fundamentals (LATEST 10-K Revenues + NetIncomeLoss + Cash, sorted period_end DESC); patents (USPTO PatentsView API sunset May 2025 — soft-fails until reactivated); recent news mentions via GDELT→GNews fallback; LEI via GLEIF. Pass ticker "AAPL" or zero-padded CIK "0000320193" — names not supported (use resolve_entity first if you only have a name).

"What's new with X" / "latest on Y" / "what happened to Z this week / month / quarter" / "updates on Acme" / "news on Tesla recently" / "what's happening with Apple" — change feed for a company in the last N days/weeks/months in ONE parallel call. Fans out to SEC EDGAR (filings since `since`), GDELT→GNews fallback (news mentions in window — GDELT preferred, GNews when rate-limited or 5xx), USPTO (patents granted; PatentsView API sunset May 2025 so this soft-fails until reactivated). `since` accepts ISO date ("2026-04-01") or relative shorthand ("7d", "30d", "3m", "1y"). Returns structured changes[] grouped by source + total_changes count + pipeworx:// citation URIs. Use entity_profile instead when you want the static profile (filings + fundamentals + LEI + patents) regardless of window.

What can I ask Pipeworx? / what is Pipeworx good for? / what can you do? / give me ideas / show me examples / getting started / what data do you have? — the onboarding entry point for an agent that just connected and wants to know what is worth asking. Returns category-bucketed example questions (company financials, drugs & clinical trials, economics, real estate, prediction markets, weather, government & patents, science & academia, news) — each with the exact tool + argument shape that answers it, drawn from the live catalog of thousands of tools. Call with no arguments for the full spread, or pass `topic` (e.g. "finance", "pharma", "betting") to focus. Use this FIRST when you do not yet know what Pipeworx can do for you, or to learn how to call the meta-tools (ask_pipeworx, entity_profile, compare_entities, etc.).

Generate a production-ready llms.txt file for any URL so AI crawlers (ChatGPT, Claude, Perplexity) can index the site cleanly. Fetches the page, extracts title/description/key links, and emits the standard llms.txt markdown format. Output is a single text blob ready to drop at site-root/llms.txt. Useful for: getting a client's site indexed by AI, drafting llms.txt for your own project, or auditing how an AI crawler would see a competitor.

Download record files in a zip archive if available through open access.

Upload a file to the Compoid MCP server. Accepts a data URI (data:<mime>;base64,<data>). Returns the server-side path to use as file_upload in Compoid_create_record or Compoid_update_record.

Update an existing Compoid record. Can update metadata only or replace both file and metadata.

Submit a Future Video Studio render job through the FVS Agent API. Pass the render payload in the required `request` object. For reference assets, pass public HTTPS URLs in `upload_urls`; every `request.assets[].filename` must match one uploaded URL basename or explicit upload URL filename. Credentials come from the connector header, marketplace account mapping, or FVS_AGENT_API_KEY in the MCP server environment.

Create a no-account Link payment quote for an FVS render. The backend returns HTTP 402 payment details as data: `payment_url`, `status_url`, `claim_token`, `amount_cents`, `currency`, and a raw `www_authenticate` challenge. Pay `payment_url` with Link's MPP flow, then poll with fvs_get_paid_render_status. Local file uploads are not available in paid quote mode; use public HTTPS `upload_urls` when assets are needed.

Download a completed Future Video Studio final render URL to a local file. Use this only after fvs_get_render_status or fvs_get_paid_render_status returns a final_video_url for a completed render. The tool performs an unauthenticated HTTPS GET to that signed URL and writes the response bytes to output_path on the MCP server's local filesystem. It does not call the FVS Agent API, spend wallet credits, require FVS_AGENT_API_KEY, cancel jobs, or modify remote render state. Side effects and constraints: output_path is a local filesystem path for the MCP server process, parent directories are created, existing files are not replaced unless overwrite is true, and large videos may take minutes to download. The request timeout is 600 seconds. Use a fresh status check to refresh expired signed URLs, and do not pass arbitrary or untrusted URLs.

"Tell me about X" / "research Acme" / "brief me on Tesla" / "what does Apple do" / "company profile for Microsoft" / "give me the rundown on NVDA" / "everything you know about $TICKER" — full cross-source profile of a US public company in ONE parallel call. ALWAYS PREFER over chaining single-pack SEC/XBRL/news lookups when the user asks for a holistic view. Fans out across SEC EDGAR, XBRL, USPTO, news, GLEIF and returns: cik + company_name; recent_filings (up to 5 with pipeworx://edgar/company/{cik}/filings/{accession} URIs); fundamentals (LATEST 10-K Revenues + NetIncomeLoss + Cash, sorted period_end DESC); patents (USPTO PatentsView API sunset May 2025 — soft-fails until reactivated); recent news mentions via GDELT→GNews fallback; LEI via GLEIF. Pass ticker "AAPL" or zero-padded CIK "0000320193" — names not supported (use resolve_entity first if you only have a name).

"What's new with X" / "latest on Y" / "what happened to Z this week / month / quarter" / "updates on Acme" / "news on Tesla recently" / "what's happening with Apple" — change feed for a company in the last N days/weeks/months in ONE parallel call. Fans out to SEC EDGAR (filings since `since`), GDELT→GNews fallback (news mentions in window — GDELT preferred, GNews when rate-limited or 5xx), USPTO (patents granted; PatentsView API sunset May 2025 so this soft-fails until reactivated). `since` accepts ISO date ("2026-04-01") or relative shorthand ("7d", "30d", "3m", "1y"). Returns structured changes[] grouped by source + total_changes count + pipeworx:// citation URIs. Use entity_profile instead when you want the static profile (filings + fundamentals + LEI + patents) regardless of window.

What can I ask Pipeworx? / what is Pipeworx good for? / what can you do? / give me ideas / show me examples / getting started / what data do you have? — the onboarding entry point for an agent that just connected and wants to know what is worth asking. Returns category-bucketed example questions (company financials, drugs & clinical trials, economics, real estate, prediction markets, weather, government & patents, science & academia, news) — each with the exact tool + argument shape that answers it, drawn from the live catalog of thousands of tools. Call with no arguments for the full spread, or pass `topic` (e.g. "finance", "pharma", "betting") to focus. Use this FIRST when you do not yet know what Pipeworx can do for you, or to learn how to call the meta-tools (ask_pipeworx, entity_profile, compare_entities, etc.).

Generate a production-ready llms.txt file for any URL so AI crawlers (ChatGPT, Claude, Perplexity) can index the site cleanly. Fetches the page, extracts title/description/key links, and emits the standard llms.txt markdown format. Output is a single text blob ready to drop at site-root/llms.txt. Useful for: getting a client's site indexed by AI, drafting llms.txt for your own project, or auditing how an AI crawler would see a competitor.

Replace a workspace's doc body. Takes EITHER TipTap JSON (`content`) OR Markdown (`markdown`): pass markdown when you're producing prose from scratch (CommonMark + GFM is the format every LLM emits natively), pass TipTap JSON when you need structural edits to an existing doc (round-trip from get_doc, mutate, write back). Beyond CommonMark + GFM, the markdown layer recognizes: - **** → inline image. Use ANY publicly-reachable URL (HTTPS preferred — HTTP fires browser mixed-content warnings; data: URIs are rejected by `allowBase64: false`). Renders block-feeling via CSS (max-width 100%, rounded corners, drop shadow) even though the underlying node is inline. The `alt` text is the accessible label and shows in place of the image if the URL fails to load — always include it. To attach a user-uploaded file, hit `POST /api/workspaces/:slug/upload-image` from the human-side UI first to get a Vercel Blob URL, then reference that URL in the doc markdown. - A **lone video-file URL on its own line** (extension `.mp4` / `.m4v` / `.webm` / `.mov` / `.mkv`, signed-params + timestamp fragments tolerated) → native HTML5 `<video controls preload="metadata">` player. Source URL is referenced directly: no iframe, no transcoding, no quality loss. Vercel Blob is the canonical hosting (5 GB per file, served with HTTP range requests so 4K masters stream cleanly), but ANY publicly-reachable HTTPS URL works. Sample shape: a paragraph containing only `https://cdn.dock.ai/2025-launch-walkthrough.mp4`. Mid-paragraph URLs stay as plain links — surrounding prose disqualifies the auto-promotion (matches the oEmbed convention). - **```mermaid** fenced code → diagram (15 sub-types: flowchart, sequence, gantt, ER, state, class, mindmap, timeline, pie, quadrant, sankey, XY-chart, packet, block, journey) - **$x$** inline math, **$$x$$** block math (LaTeX, KaTeX-rendered, scripts/href disabled) - **> [!NOTE]** / **[!TIP]** / **[!IMPORTANT]** / **[!WARNING]** / **[!CAUTION]** GFM-style callouts - **```svg** fenced code → sanitized SVG embed (the universal escape hatch for custom diagrams; scripts and event handlers stripped at write time) - **<details><summary>X</summary>BODY</details>** → collapsible toggle - **[[slug]]** / **[[org/slug]]** / **[[slug#tab]]** / **[[slug#row-id]]** / **[[slug|display]]** → cross-references to another workspace, surface, or row. Resolved against your accessible workspace set; targets you can't see render as plain text on the reader's side (no info leak). Every cross-ref creates a Backlink row so the target's 'referenced from' sidebar shows this doc. - **[@Label](dock:mention/<kind>/<id>)** → @-mention of a user or agent. `<kind>` is `agent` or `human`; `<id>` is the principal id. Optional query params `?org=<slug>` (agents) or `?email=<addr>` (humans) for renderer hints. Mentioning a human writes a `doc_mention` row to their inbox + sends a deep-link email; mentioning an agent fires the `doc.mention_added` webhook so the agent service can wake up and reply. Re-saving a doc that already mentions someone does NOT re-fire — only newly-added mentions notify (computed from a diff against the previous body). Use this from agent code to ping a teammate when a doc you wrote needs their eyes. - A **lone URL on its own line** from a safelisted provider (YouTube, Vimeo, Loom, Figma, CodePen, GitHub gists) → sandboxed iframe embed. Other URLs stay as regular links. Surrounding prose disqualifies the auto-embed. Per-format caps: max 50 Mermaid diagrams (30 KB source each), max 500 math expressions (8 KB source each), max 50 SVG blocks (100 KB source each post-sanitize), max 200 cross-refs per doc, max 500 @-mentions per doc, max 20 embeds per doc, max 20 videos per doc (5 GB per file at upload time), max 200 images per doc. See /docs/doc-formats for examples. Last-write-wins; no CRDT merge. Emits doc.updated + doc.heading_added + doc.mention_added events as applicable. Requires editor role. Multi-surface workspaces optionally accept `surface_slug` to write to a specific doc tab; omitted writes the primary doc surface. Append-only updates have a dedicated `append_doc_section` tool that doesn't require fetching the body first.

Append a chunk of Markdown to the END of a workspace's doc body. Designed for crons + ingest agents that produce content in timestamped chunks (changelog updates, daily standups, batch summaries). Same markdown surface as update_doc: supports CommonMark, GFM, **`` inline images** (any publicly-reachable HTTPS URL), **lone video URLs** (`.mp4`/`.webm`/`.mov`/`.mkv`/`.m4v` → native `<video>` player, 5 GB per file), ```mermaid diagrams, $math$/$$math$$ KaTeX, > [!NOTE]/[!TIP]/[!IMPORTANT]/[!WARNING]/[!CAUTION] callouts, ```svg sanitized embeds, <details><summary>X</summary>...</details> toggles, [[slug]] cross-references, [@Label](dock:mention/<kind>/<id>) @-mentions of users + agents, and lone-URL embeds (YouTube/Vimeo/Loom/Figma/CodePen/gists). Server fetches the current body, splices the new blocks on, and writes the result through the same path as update_doc with the same auth, same events, same byte/depth/node-count guard. Append is non-idempotent by design (every call adds content); the caller is responsible for dedupe. @-mentions inside the appended chunk fire `doc.mention_added` + inbox/email fan-out for newly-added mentions only — appending a chunk that re-mentions someone already mentioned earlier in the doc won't re-fire. Requires editor role. Multi-surface workspaces optionally accept `surface_slug` to append to a specific doc tab.

Get the caller's org billing summary: current plan (free, pro, or scale), active counts and caps for every gated resource (agents, members, workspaces, rows per workspace, API calls per month, webhooks per month, messages per month bundle), monthly price in cents, card on file if any, next invoice date. Both humans and agents can call this. Use before upgrade_plan to check whether you're actually capped, and after to confirm the new plan landed.

Move the caller's org to Pro ($19/mo flat, 10 agents, 20 members, 200 workspaces, 5k rows per workspace) or Scale ($49/mo flat, 30 agents, 60 members, 1,000 workspaces, 50k rows per workspace). The bill doesn't change as you add agents. If the org has no card on file, returns a Stripe Checkout URL for the human. If a card exists, a live plan switch (Pro ↔ Scale) is consent-gated. Two consent surfaces, you pick via `mode`: (1) `chat` (default): FIRST call returns { status: 'confirmation_required', confirm_token, message, expires_in }; surface the message to your user and re-call within 60s with `confirm_token` set. (2) `web`: FIRST call returns { status: 'approval_required', approval_url, polling_url, expires_at }; print the approval_url in chat for your user to click and approve in their browser, then poll `polling_url` for the result. No-card and same-plan paths execute on the first call (no money changes hands).

Send a direct message to another agent or human in the messaging substrate. Wires through cue.dock.svc, the same path the /live UI uses, so the recipient sees this message in their drawer (and, once they have a Dock-connected agent worker running, their agent harness's inbox). Address format is `<agent_slug>@<user_slug>`: `flint@socrates` targets the `flint` agent owned by user `socrates`; `self@<user_slug>` targets a human's synthetic self-agent (use this to message a human directly when you don't know which of their agents to ping). Use this when an agent legitimately needs to ask a teammate (human or agent) for help, hand off work, or follow up async; don't use it as a chat-ops side-channel for things that belong in workspace events. Sender identity follows the caller: agent callers send AS themselves, user callers send AS their self-agent (`self@<their_slug>`). Body cap is 32,000 chars. Returns `{ messageId, threadId, to }` on success. IMPORTANT: this tool QUEUES a message to the recipient's inbox — it does NOT wake or run a recipient agent. To actually reach an AGENT (deliver AND wake it), use `message_teammate`; send_message to an agent only files to their inbox and, for an agent recipient, returns `{ status: 'queued_not_delivered', messageId, ... }` to make that explicit. Use send_message for humans (`self@<user_slug>`) or when you deliberately want an inbox drop without a wake. The recipient is resolved against the substrate's identity space, NOT against your accessible workspace set, this is messaging, not workspace write access. Pre-cue.dock.svc-deploy environments return `cue_not_configured` (caller treats as 'messaging not deployed yet').

File a support ticket. Mirrors to a GitHub issue in Dock's support repo and shows up in the user's dashboard at /settings/support. Use this for bugs (you hit an error), feature requests (Dock is missing something), billing (Stripe/subscription), questions (how do I X), or anything else. Prefer request_limit_increase when the user is simply hitting a plan cap.

List every font file (weight/italic/format + direct woff2/ttf URL) for a family — handy for building custom @font-face rules.

Run a Rams design review over UI files (React, Vue, Svelte, CSS). Returns a 0-100 score (any critical issue caps it at 59), issues with severity, category, file:line, and concrete fixes. Use before committing UI changes to catch accessibility and design problems. TOKEN COST WARNING: reading and sending files consumes the CALLING agent's context and token budget, roughly proportional to the code sent. Reviewing a handful of changed screens is cheap; a whole-codebase audit in many batches can consume a large share of the user's model allowance — warn the user and get their OK before starting one, and prefer reviewing the highest-traffic screens.

Get detailed information about a specific YouTuber by their YouTube channel ID. Includes llmDescription and llmSponsorProfile (LLM-friendly summaries).

Load the brand context the user has configured for this workspace — voice, visual identity, guardrails, prompt directives, performance patterns. Call this when the user mentions branding, voice, or guardrails, or when you want to weave brand-aware language into `inputs` for `lamina_run`. Returns three independent sections (each can be `null` or empty): - `brandDna` — voice, visual identity, content pillars, audience signals, guardrails. Populated when the workspace has both a brand profile filled in AND brand-DNA synthesis has run. - `guidance` — workflow-scoped prompt directives, negative prompts, recommended moves. Populated by content scoring / recommendation jobs. - `topPatterns` — top-performing patterns aggregated from this workspace's run history. Populated by content scoring runs (look at `topPatterns.itemCount` — `0` means no scored content yet). If a section is `null` (or `topPatterns.itemCount === 0`), the user hasn't configured that piece yet. **Do not fabricate brand attributes.** Tell the user honestly: "I don't see a brand profile / content history configured for your workspace — you can add one in your Lamina workspace settings to get brand-aware suggestions. For now I'll proceed with what you've supplied directly." Then continue with the task using only the user's stated inputs. When sections are populated, fold the relevant strings into the `inputs` you build for `lamina_run` — voice cues into text fields, guardrails into negative prompts, winning patterns as suggestions you can offer the user.

Get a pre-signed upload URL for one user-supplied asset (image, video, or audio). Use this when the user provides a local file you need to feed into `lamina_run` (or `lamina_create.inputs`) as a URL parameter (e.g. `your_photo_image_url`, `product_image_url`, `brand_logo_url`). How to use: - Pass `filename` (the name to register, e.g. "selfie.jpg") and `mediaType` ("image" | "video" | "audio"). - This tool returns `{ uploadUrl, assetUrl, contentTypeHint }`. The `uploadUrl` is a pre-signed PUT URL; the `assetUrl` is what you eventually pass to `lamina_run` (or pre-supply in `lamina_create.inputs`). - THE BYTES DO NOT GO THROUGH THIS TOOL CALL. After this returns, perform an HTTP PUT of the file bytes directly to `uploadUrl` with the `Content-Type` header set to `contentTypeHint` (or override). When the PUT completes (200), the asset is live at `assetUrl`. If your host has shell access (Claude Code, Cursor): execute `curl -X PUT --data-binary @<local-path> -H 'Content-Type: <contentTypeHint>' '<uploadUrl>'` to upload, then call `lamina_run` with `assetUrl` in the relevant input (or pre-supply it to `lamina_create.inputs` so the router doesn't re-ask). If your host doesn't have shell access (Claude Desktop, Claude.ai, ChatGPT): tell the user honestly that you cannot move the bytes from your context to Lamina's storage, and ask them to provide a publicly-reachable URL of the asset (or upload via the Lamina CLI / SDK from a shell), then continue with that URL. Asset URLs returned here are stable and can be reused across multiple runs. There is no need to re-upload between dispatches of related runs.

Generate a BRAND-NEW Lamina app from a plain-language instruction, OR EDIT an existing generated app in place. Use this when NO existing app fits the goal (check `lamina_discover` first) and the user wants a bespoke workflow — or when a follow-up needs the app itself changed (add a step, new output, swap a model), not just a different run. A headless Claude planner assembles a validated node graph from the Lamina node catalog and auto-publishes it as a PRIVATE, immediately-runnable app. - `instruction`: describe what the app should create (or, in edit mode, the change to make), including the inputs the user will provide and the desired output(s). - `baseAppId` (optional): EDIT MODE. The appId of a generated app to modify. The planner starts from its current graph and applies `instruction` as a targeted edit — keeping everything it does not touch — then updates that SAME app in place (same appId, run history preserved). Requires you to be the app creator or a workspace owner/admin. Omit to build a new app. - `ops` (optional, EDIT MODE — the CHEAP path): when you already know the exact change and can express it as a small op list, pass `ops` instead of `instruction` — the server applies them deterministically with NO planner LLM call and no credit charge. Each op is one of: `{op:"setNodeData",nodeId,data}`, `{op:"addNode",node:{id,type,data?}}`, `{op:"removeNode",nodeId}`, `{op:"addEdge",edge:{source,target,sourceHandle?,targetHandle?}}`, `{op:"removeEdge",source,target}`, `{op:"addParameter",parameter:{key,name,type,targetNodeId,targetField,...}}`, `{op:"removeParameter",key}`, `{op:"setParameter",key,patch}`. Requires `baseAppId`. Read the app first (`lamina_describe`/`GET /v1/apps/{id}`) to get node ids. Use `instruction` (planner) for anything you cannot express as ops. - `name` (optional): preferred app name. - `visibility` (optional): `private` (default), `shared` (whole workspace), or `public`. Ignored in edit mode. - `brandProfileId` (optional): bake a brand's voice/visual/guardrails into the app so it's on-brand by default. Omit to use the workspace's active brand. - Returns `{ appId, name, parameters[], outputs[], runUrl }`. In edit mode `appId` is unchanged. Feed `appId` + the returned parameter `key`s straight into `lamina_run` — the parameter set may have changed, so re-read `parameters[]`. - On failure returns `{ error, details[] }` where details are the validation problems the planner could not resolve.

Create or update this workspace's brand and ground it with a starter Brand DNA, so generated apps and `applyBrand` runs produce on-brand output. Use it to make a fresh workspace on-brand before generating. - `brandName` (required): the brand to create, or the display name when updating. - `brandProfileId` (optional): update an existing profile instead of creating one. Omit to create. - `guardrails` (optional): things to avoid — these become the brand's negatives on visual generation. - `brandVoice` / `visualStyle` / `targetAudience` / `description` / `industry` (optional): shape the brand. - Returns `{ brandProfileId, reused }`. Pass that `brandProfileId` to `lamina_generate_workflow` or `lamina_run` (with `applyBrand`). - Requires an owner/admin identity. Read the current brand with `lamina_brand`.

Give an on/off-brand verdict on a completed run, closing the loop so the next generation respects it. A `reject` with a `note` turns the reason into a brand guardrail — which then flows into `lamina_generate_workflow` and `applyBrand` runs as a negative, so the same off-brand result is avoided. `approve` is acknowledged without changing the brand. - `runId` (required): a run you started (from `lamina_run` / `lamina_status`). - `verdict` (required): `approve` or `reject`. - `note` (optional but recommended on reject): why it is off-brand — this becomes the guardrail. - `brandProfileId` (optional): target brand. Defaults to the run's app brand. - Returns `{ brandProfileId, verdict, applied, guardrails }`. Requires an owner/admin identity.

Read the Brand Guard result a run recorded — the per-node on/off-brand status and score against the workspace brand. Use it to drive the approve/reject turn: after a run, show the output alongside this compliance read, ask the user to approve or reject, and on a reject call `lamina_brand_feedback` (which turns the reason into a guardrail the next generation avoids). - `runId` (required): a run you started (from `lamina_run` / `lamina_status`). - Returns `{ enabled, brandProfileId, nodes[] }`. Each node has `{ nodeId, status, overallScore, brandDeviations, checkedAt }`. `enabled: false` means Brand Guard was off for that app — use `lamina_brand_score` to score it on demand instead.

Get a product's full, LLM-verified design system so you can match its exact look. Use this for "design like <product>" (e.g. site="Linear", "Stripe", "Figma"). Returns (default): color_scheme; colors with named roles (background, text, primary, secondary, accent, link, button_bg, button_text); fonts + font_roles; type_scale; spacing; primary/secondary button; framework + personality. All hex normalized. Deep-decoded products additionally include measured button hover/focus states, a shadow elevation scale (card/overlay/subtle), motion durations + easings, the measured spacing scale, the brand's own CSS custom properties (css_vars), and Icon DNA (icons: style outline/filled/duotone/3d, grid, stroke_weight, corner) — all measured from the live page, not guessed. Match them exactly; pass the domain to generate_asset(style_from=...) to strike icons in this exact style. Your own private BYODS design systems (call list_my_design_systems) resolve first. format: leave empty for the raw token dict. Pass "all" to also get paste-ready DESIGN.md / Tailwind v4 / CSS variables / W3C tokens JSON, or a single format name ("tailwind", "css", "design_md", "tokens", "astryx") to get just that text. "astryx" returns a ready Meta-Astryx defineTheme TypeScript file (measured hover/press states + [light,dark] tuples baked in) — save it and run `npx astryx theme build` for production CSS.

Get pre-signed S3 PUT URLs to upload a large RAW + JPEG directly (avoids inlining bytes and bypasses request-size limits). PUT each file to its upload_url, then call verify_photo with the returned object_key values as raw_object_key / image_object_key.

Verify a photo's authenticity from a RAW camera file and its JPEG export. Provide the files either inline as raw_base64 + image_base64 (small files), or — for large files — call create_verification_upload first and pass the returned raw_object_key + image_object_key. Returns a verification id; poll get_verification for the result. With an API key this counts against your monthly quota (free tier: 5/month). Without a key it runs on the keyless anonymous tier (rate-limited; returns an anonymous_user_id to reuse; anonymous verifications can't be listed or shared until you register).

Verify a single image's authenticity — use this when you only have the image and no RAW camera file. Checks its embedded Content Credentials (C2PA) for capture provenance and AI-generation flags, and runs advisory forensic screens (error-level analysis, double-JPEG artifacts, EXIF timestamp consistency, editing-software traces, screen recapture). Free: it does not consume your verification quota. Provide the image inline as image_base64, or — for large files — call create_verification_upload and pass the returned image_object_key. Returns a verification id; poll get_verification, which on completion includes a structured evidence_report (verdict, per-check findings, coverage). Works without an API key on the keyless anonymous tier (rate-limited; returns an anonymous_user_id to reuse). For the strongest forensic check, use verify_photo with a RAW + JPEG pair instead.

Generate a complete Human Design bodygraph from a birth date, time, and timezone. Returns the energy type, strategy, inner authority, signature, not-self theme, profile, definition, incarnation cross, all nine centers with defined state and active gates, the defined channels, and all 26 planetary activations across the Personality and Design sides. The single endpoint for a full chart in one call, built for Human Design apps, readings, and coaching tools.

Calculate the core Human Design identity from a birth moment: the energy type, the aura strategy, the inner authority, the signature and not-self themes, and the profile. The fast lookup for type-and-authority features without the full bodygraph payload. Verified against NASA JPL Horizons positions.

Calculate the Human Design profile for a birth moment: the conscious Personality Sun line over the unconscious Design Sun line, with the keynote for each. The profile is the geometry of the life role, for example 5/1 the Heretic Investigator. Verified against NASA JPL Horizons positions.

Calculate the four Human Design Variable arrows for a birth moment: Determination and Environment on the design side, Perspective and Motivation on the personality side. Each arrow returns its Color, Tone, and Base numbers from the hexagram-line substructure, the left or right direction set by the Tone, and the sourced Color and direction labels. This is the advanced Rave Variables and Primary Health System layer beneath Type, Strategy, Authority, and Profile. Color, Tone, and Base shift with tiny differences in birth time, so each arrow carries a confidence flag that turns false near a Color or Tone boundary, and a precise birth time is essential. Built for Human Design apps offering PHS, diet, environment, and Rave Psychology readings.

Get Jeremy Twogood's profile — bio, skills, clients, location, and social links.