Skip to main content
@pureframeai/mcp is the package that turns your Pureframe AI library into an MCP server. For per-client setup instructions (Claude, Cursor, VS Code, Codex, OpenCode), see Connect an Agent: this page covers the package itself.

​
Running it locally

Most clients invoke this for you via npx, so there’s usually nothing to install manually:
It reads PUREFRAME_API_KEY from the environment and speaks MCP over stdio: this is what every client config in Connect an Agent points at.

​
Remote endpoint

Pureframe AI also provides a hosted MCP endpoint at https://mcp.pureframe.ai. Use it with clients that support remote MCP when you do not want to run Node.js locally. The remote endpoint cannot read your local filesystem, so upload_video is available only through the local server.

​
Tools exposed

The server provides search_videos, list_collections, get_collection, get_video, upload_video (local only), and get_job_status. See MCP overview for details about each tool.

​
Source

The package wraps the same REST API as the Python and JavaScript SDKs. If you need a capability the MCP tools don’t expose, call the REST API or an SDK directly alongside it.