Connect via MCP

MCP (Model Context Protocol) is an open standard that connects AI tools to external services. Connected to CutPro, the model runs the whole flow on its own: it analyzes the video, clips it, renders it and hands back the link.

Note

API access requires the Pro plan. Create a key in API keys and use it as CUTPRO_API_KEY.

Local: Claude Code, Cursor, VS Code

The server runs on your machine through npx and exposes the v1 API endpoints as tools, covering workspace, balance, videos and uploads, clipping, clips, templates, renders, publishing and connections.

Claude Code

claude mcp add cutpro \
  --env CUTPRO_API_KEY=$CUTPRO_API_KEY \
  -- npx -y @cutpro/mcp

Claude Desktop, Cursor, VS Code

MCP server configuration

{
  "mcpServers": {
    "cutpro": {
      "command": "npx",
      "args": ["-y", "@cutpro/mcp"],
      "env": { "CUTPRO_API_KEY": "your_key" }
    }
  }
}

Tip

Multi-workspace key? Add CUTPRO_WORKSPACE_ID to the env as well.

An example

Once connected, just ask in plain language:

“Analyze this YouTube video, generate the clips, and send me the 3 best-rated ones already rendered.”

The AI chains the tools by itself: analyze_video, submit_clipping, get_submission (until it finishes), list_clips, render_clip, get_render and get_render_download.

Remote: ChatGPT and Claude.ai

The same server runs at https://mcp.cut.pro with full OAuth 2.1 (metadata discovery, dynamic client registration, PKCE and refresh tokens). It is the path for clients that run in the cloud and cannot execute npx.

1. Add the connector

   In ChatGPT (Connectors) or Claude.ai (Settings, Connectors, Add custom connector), enter the URL https://mcp.cut.pro.

2. Authorize with your key

   The client opens a consent page. Paste your API key: it is validated and access is granted.

3. Done

   The client can now use CutPro tools in conversations.

Let the AI read these docs

For questions about the product, without running anything, the documentation is published as plain text in the format models read directly:

Address	What it holds
/docs/llms.txt	The index of every page, in all three languages
/docs/llms-full.txt	The whole documentation in a single file

Paste either one into a conversation and ask away. Any page also answers in Markdown if you swap the URL for .md, as in /docs/en/api-reference/quickstart.md.

Next step

Rather call the API directly?

The Quickstart has the whole flow in curl, Node.js and Python