Clipwright

@clipwright/mcp-server

Your coding agent writes the script; Clipwright renders a short vertical video of an actor speaking it, 1080×1920 by default. It also makes faceless videos of up to 90 seconds from a script or a short brief: narration over an opening animated clip and image scenes, with no on-camera presenter. The agent asks for a free quote before it spends anything, and whatever the API cannot honor comes back in warnings[] instead of being dropped silently.

The agent gets a run_id at once and polls until the video URL is ready. Clipwright returns the file; it does not publish anywhere. Quotes, voices, actors and the account balance are free. Renders spend credits: an account opened by signing up starts with 420 trial credits, enough for one 90-second faceless video. Buy more at clipwright.io/pricing.

Install

There are two ways to connect: the hosted server at https://mcp.clipwright.io/mcp, or this package run locally over stdio. Both serve the same tools.

Hosted server, no key

Add the URL to your client. On first use the client opens a browser, you sign in to Clipwright and approve the app. Claude Code and the device-code flow below were verified live on 2026-10-18; the other commands come from each client's own documentation and have not been tried with Clipwright yet.

• Claude Code (verified live): claude mcp add --transport http clipwright https://mcp.clipwright.io/mcp, then run /mcp in a session and sign in.
• Claude.ai and Claude Desktop: Customize → Connectors → Add custom connector, then paste the URL.
• ChatGPT: add the URL as the remote MCP server of a plugin, as OpenAI's guide "Connect and test your plugin" describes; ChatGPT signs in with OAuth.
• Cursor: in ~/.cursor/mcp.json, {"mcpServers": {"clipwright": {"url": "https://mcp.clipwright.io/mcp"}}}.
• VS Code: in .mcp.json at the workspace root, {"mcpServers": {"clipwright": {"type": "http", "url": "https://mcp.clipwright.io/mcp"}}}.
• Gemini CLI: gemini mcp add --transport http clipwright https://mcp.clipwright.io/mcp, then /mcp auth clipwright.
• Codex: codex mcp add clipwright --url https://mcp.clipwright.io/mcp, then codex mcp login clipwright.

The approval page lists the permissions the app asks for. There are two:

• mcp:read — the tools marked read-only: account, runs, shots, voices, actors, workflows and quotes.
• mcp:write — every other tool. Some start paid runs and spend credits; the rest change the account (actors, uploads, workflow plans).

A connection without mcp:write gets 403 insufficient_scope from those tools, and nothing is charged. Only an admitted account can approve.

To disconnect an app, open app.clipwright.io/api-keys, find it under Connected apps and revoke it. Its next request gets 401. A connection lasts 90 days from approval; after that the app asks you to sign in again.

On the hosted server upload_image cannot read a file on your machine. Pass a public https URL as upload_image({url}) and the server downloads it, or call create_upload and PUT the file to the returned put_url with curl. Either way you get an upload_id for first_frame, last_frame and references.

An agent with no browser signs in with a device code and the first-party client clipwright-agent (verified live 2026-10-18):

curl -s https://mcp.clipwright.io/device/auth -d client_id=clipwright-agent \
  --data-urlencode "scope=mcp:read mcp:write offline_access" \
  --data-urlencode "resource=https://mcp.clipwright.io/mcp"

Open verification_uri (https://mcp.clipwright.io/device) on any device, enter user_code, sign in and approve; the approval page repeats the code. Meanwhile poll POST https://mcp.clipwright.io/token with grant_type=urn:ietf:params:oauth:grant-type:device_code, the device_code and client_id=clipwright-agent, no more often than every 5 seconds: a faster poll gets slow_down. Send the access_token as Authorization: Bearer to /mcp; it lasts an hour. Renew it with grant_type=refresh_token and keep the newest refresh token each time. The device flow is open to this client only.

Hosted server with a cw_* key

For CI and scripts, send a key instead of signing in. A key holds both permissions.

claude mcp add --transport http clipwright https://mcp.clipwright.io/mcp --header "Authorization: Bearer cw_..."

n8n

n8n's built-in MCP Client node calls one tool per node:

• Server Transport: HTTP Streamable; MCP Endpoint URL: https://mcp.clipwright.io/mcp.
• Authentication: Bearer Auth, with a credential whose token is your cw_... key.
• Tool: pick from the list, for example quote_ugc; Input Mode: JSON.

Verified live on 2026-10-20 with self-hosted n8n 2.43.8: get_account, quote_ugc and get_run returned through the node. A workflow to import, n8n/clipwright-ugc.json in seocombat/clipwright-mcp, quotes a script, stops when the quote is above max_credits, starts make_ugc and polls get_run every 15 seconds. The whole workflow ran on n8n Cloud on 2026-10-20 and returned a 1080×1920 MP4 in about three minutes. n8n's OAuth credential has not been run against Clipwright yet.

Local server over stdio

claude mcp add clipwright -e CLIPWRIGHT_API_KEY=cw_... -- npx -y -p @clipwright/mcp-server clipwright-mcp

Put your own key in place of cw_.... The command is one line and gives the shell nothing to expand, so bash, zsh and PowerShell run it alike. It needs Node.js 20 or newer.

Any MCP host works — the local server speaks JSON-RPC over stdio. Issue keys at app.clipwright.io/api-keys.

Environment

These variables configure the local server.

Variable	Required	Meaning
CLIPWRIGHT_API_KEY	yes	Your cw_* token. The process exits immediately without it.
CLIPWRIGHT_CLIENT_ID	recommended	Identifies this installation and enters the idempotency key, so two installations never collapse into one run. Left unset, the server keeps one in ~/.clipwright/client-id, which suits a single laptop. Set it yourself where a home directory is shared, cloned or read-only — containers, CI, copied images — as SKILL.md §2 explains.
CLIPWRIGHT_API_URL	no	Defaults to the hosted API.

Recipes

Each recipe is a prompt we gave an agent with this server connected, the call the agent sent, and what the video cost. The videos play at clipwright.io/mcp.

1. A creator reel with on-screen graphics

One presenter on camera, with graphics over her that react to what she says: the format of talking-head reels that sell a product. One prompt, no editor.

The prompt, given verbatim, with our actor id, screenshot link and site named alongside it:

Make a 30-second vertical reel for my AI receptionist with my presenter actor and the voice Hope. Script: "Every missed call is a lost deal. Your receptionist sleeps, takes breaks, and sometimes gets annoyed. This one doesn't. It answers calls all day, works around the clock, and never gets annoyed. Here's a real one: a customer calls at two in the morning to book a cleaning, and it handles everything, the time, the price, the confirmation text. Small businesses miss a third of their calls. Not anymore. Set it up in ten minutes and stop losing deals while you sleep."

While she lists what it does, show a checklist with three switches ("answers calls" and "works 24/7" off, "gets annoyed" on) and have a cursor flip each one as she says it. When she gets to the 2 a.m. customer, show an incoming call from +1 (305) 555-0147 on the right and answer it on "handles". Put my dashboard screenshot in the top right corner while she says "Small businesses miss a third of their calls." End on a card with my site and "create your assistant". Caption only the key lines, in the highlighter style, and zoom in a little on "Not anymore." Quote it before you render.

What the agent sent: one make_ugc quote with templates (checklist, phone_call, end_card), one overlays picture, caption_mode: "highlights", caption_style: "highlighter" and a punch_in on one emphasis line. Click, switch and ring sounds come with the templates by default. We checked the prompt with a fresh agent on this server on 2026-10-24; the video was rendered from the same call.

Price: 400 credits for 33 seconds. The quote named the price before anything was spent. Watch it.

Tools

• list_workflows — read workflow methods and current availability. Free.
• get_workflow — read one method's required inputs, script rules, evidence and limitations. Free.
• prepare_workflow_plan — create with a complete document, or save with both plan_id and base_version. Free; starts no run.
• get_workflow_plan — read the current owned plan, revision and readiness. Free.
• approve_workflow_plan — explicitly approve a chosen revision and content digest. Free; starts no run.
• quote_workflow_plan — quote the approved revision without spending credits.
• run_workflow_plan — start a paid workflow using its exact quote fields and an explicit idempotency key. Returns its receipt and run id immediately; poll get_run. Recover an uncertain purchase with the original request and key.
• list_voices — voices for voice: the presets, the thirty voices of the speech model gemini-3.8-flash-tts and the catalog for make_ugc, with filters by language, gender, age, use case and model, and a short audio sample where the voice has one. The seventeen narration voices of make_faceless are listed with skill: "make_faceless". Free, spends no credits.
• list_template_sounds — the sounds make_ugc templates play, by beat: where each beat plays, its default and every name template_sounds takes. Free.
• list_actors — ready-made faces with stable ids and verified formats. Free.
• quote_ugc — estimated duration and price, plus a warning when make_ugc with the same input would be refused for money or access. Free.
• get_account — balance, debt and holds of the account. Free.
• make_ugc — renders a clip; this is the call that costs money. Returns a run_id immediately instead of blocking, because a render takes minutes.
• get_run — status of a run. Free; poll it every few seconds.
• get_run_shots — the shots of a finished video: the span, kind, description and preview link of each, with the narration words and their timing. Free and read-only. A run with no shots to show answers with the reason instead.
• quote_revision — price of a revision of a faceless video: what it would change and what it costs. Free.
• revise_run — starts a revision: a new run that renders the video again with the shots you change; this costs money. Pass changes (a shot and what to generate for it) or the whole edited document. A revision that delivers is charged its quoted total; one that fails is charged nothing, even when its paid work was already done. An identical request returns the same run; attempt starts a second one on purpose. Returns a run_id immediately; poll get_run until succeeded.
• quote_candidate — price of a shot candidate of a faceless video: one picture or clip made for one shot, to keep or discard in a revision. Free.
• create_candidate — makes a shot candidate; this costs money. Pass the shot and the operation to generate for it. A delivered candidate is charged its one unit whether it is kept or discarded; one that fails is charged nothing, even when its paid work was already done. An identical request returns the same run; take makes another candidate on purpose. Returns a run_id immediately; poll get_run until succeeded.
• list_generation_models — the models of single generations with their measured shapes and credits per image or per second. Free.
• quote_image, quote_video — price of one image or one clip. Free.
• generate_image, generate_video — make one image or one silent clip; this costs money. One that fails is charged nothing, even when the vendor was already paid. An identical request returns the same run; attempt starts another on purpose. Poll get_run; generation.url is the file.
• upload_image — a PNG/JPEG from a local path or a public https url → upload_id and a signed https url to pass as image. Free; 20 per day, at most 30 url downloads per hour, the url lives 24 hours. Set aspect_ratio explicitly afterwards.
• create_upload — a presigned PUT for a local PNG/JPEG when the server is remote: PUT the file with curl, then use the upload_id. Free.
• get_upload — one upload with a fresh url, its size and usable_until; after create_upload it confirms the PUT. Free.
• create_asset — save a picture or an MP4 clip as an account asset, kept until you delete it: from a run_id, an upload_id, a public url (a clip with kind: "video"), base64, a presigned put, and a local path on stdio. A clip is checked in the background: get_asset says when it is ready. Your own material needs rights_confirmed: true once. Free; 2000 assets and 20 GB per account, 100 new ones per day.
• list_assets, get_asset — the account's assets with fresh urls and the usage of the caps. Free.
• update_asset — rename an asset or change its role. Free.
• delete_asset — delete an asset; a daily cleanup removes its file once 7 days have passed. Free.
• quote_actor — price of a personal actor before creating one. Free.
• create_actor — creates a personal actor from a description; this costs money. Each requested format is a separate charged image. Returns a run_id immediately; poll get_run until succeeded, then pass created_actor.actor_id to make_ugc as actor_id.
• quote_faceless — price of a faceless video before making one. Free.
• make_faceless — makes a faceless video from your script or from a short brief; this costs money. You pick 30 to 90 seconds; the video ends with its narration, from 25 seconds to a quarter past your pick (never past 90), and costs at most the quote. Narration plays over an opening animated clip and image scenes, with captions on by default. voice picks the narration voice by name. Returns a run_id immediately; poll get_run until succeeded.
• delete_actor — removes a personal actor of this account. Videos already made with it stay as they are. Free.
• get_actor_defaults, set_actor_defaults — read and save an actor's B-roll default. It is stored only: today's talking-actor videos do not use it. Free.

Call quote_ugc before make_ugc: the quote is where the contract tells you what it will and will not honor. Anything the API cannot deliver comes back in warnings[] rather than being dropped silently, and unsupported fields are rejected up front instead of being accepted and ignored.

Bumping the attempt field starts a new paid render. It is the way to retry a failed run on purpose, not a free refresh. For faceless videos attempt belongs to make_faceless: a quote takes none, and quote_faceless refuses it.

SKILL.md ships inside the package with the full operating instructions, and CHANGELOG.md next to it says what changed in each release and what was removed.

Privacy

The server sends your script or brief, chosen options and any uploaded image to the Clipwright API to quote and render the video. How that data is handled: clipwright.io/privacy. Documentation: clipwright.io/docs.