Draftless MCP for any AI
Connect Draftless to your workflow and generate images, video, audio, text and 3D directly from your prompts — in Claude, ChatGPT, Cursor, Codex, Gemini CLI and more.
Connect in under a minute
Pick your client, copy the endpoint, and sign in with OAuth — no API key to manage.
Add the Draftless connector to Claude
In Claude web or Claude Desktop: Settings → Connectors → Add custom connector. Name it “Draftless” and paste the server URL.
Your Draftless endpoint
Connect and start creating
Sign in with your Draftless account when the browser opens — OAuth handles everything, no API key to manage. Then ask Claude to generate an image, a video or a full faceless episode.
Sign-in and consent happen in your browser on first connect — approved on draftless.dev/connect.
Prefer the terminal? Switch to the for Claude.
How does MCP work?
“Make me a 4-second cinematic aerial of green sea cliffs at sunrise, waves breaking below, with sound.”
Your agent picks the right video model, quotes the credits, waits for your go-ahead, then polls the job to completion and hands back the finished MP4.
discovergeneratejobsJust describe it, Draftless builds it
One prompt in the client you already use — Draftless picks the models, quotes the cost, waits for your yes, and hands back the finished file.
You
“Make me a 4-second cinematic aerial of green sea cliffs at sunrise, waves breaking below, with sound.”
Draftless MCP
recommend_pipelinepicked Veo 3.1 · 4 s · 16:9 · audio onexecute_chainquote: 150 credits — confirm before spending?Approved by you — 150 credits
get_video_statusrendering… done
Credit-spending tools always return a cost estimate and need an explicit confirmation before any credits are used.
Prefer a terminal?
The same models, credits and workflows from the command line — or bundled as a skill your coding agent can pick up on its own.
Draftless CLI
Log in once, then list models and prices, check your balance, run a workflow, or render one asset per row of a CSV.
npx @draftless/cli login
npx @draftless/cli models --type video
npx @draftless/cli credits
npx @draftless/cli batch product-hero --csv products.csv --out ./outAgent skill bundle
Drop the Draftless skill into Claude Code or any agent that reads a skills folder. It knows the commands, and that it must quote the cost before spending.
cp -r skills/draftless ~/.claude/skills/draftlessOne credit balance for the web app, every plugin and your assistant
Installing is free. Generations spend credits from your plan, and every run shows its price before you confirm. New accounts start with 100 free credits.
Creator
Hobbyists and side projects
€19/ month
1,260 credits a month
Pro
Freelancers and small teams
€39/ month
4,400 credits a month
Studio
Most popularAgencies and content studios
€99/ month
12,650 credits a month
Scale
High-volume teams
€299/ month
42,000 credits a month
Questions
What is the Draftless MCP server?
A hosted Model Context Protocol endpoint. Add it to an assistant that supports MCP and that assistant can generate images, video, audio and 3D with Draftless, track the jobs and hand you the results.
Do I need an API key?
No. The first time you connect, your browser opens and you sign in with your Draftless account through OAuth. There is no key to copy, store or rotate.
Which assistants work with it?
Claude, ChatGPT (Developer Mode), Cursor, Claude Code, Codex CLI, Gemini CLI, VS Code, Windsurf, Cline and any other client that supports remote MCP servers over HTTP.
What does it cost?
Connecting is free. Generations spend credits from the same balance as the web app and the plugins, and the assistant can ask for the exact price before anything is spent.
Where do the results go?
Into your Draftless Asset Library, next to everything you make on the web and in the plugins. Signed in, you can review every call your assistant made on the MCP activity page.