Pureframe AI API Documentation

The Pureframe AI MCP server lets compatible AI clients search footage, list collections, retrieve video details, and upload footage when permitted. Try asking your agent: “Find the segment where our CEO mentions pricing.”

What is MCP?

The Model Context Protocol (MCP) is an open standard for connecting AI clients to tools and data sources. Configure the Pureframe AI MCP server to expose its tools to a compatible client.

How it works

You send a natural-language request to the model.
The model calls search_videos with a query and optional collection scope.
Pureframe AI returns matching segments and supporting fields.
The model uses the returned frame or text to answer and cite the source.

Available tools

Tool	Description
`search_videos`	Find moments matching a text query. Returns clips with timestamps, presigned URLs, and base64-encoded frame images
`list_collections`	List all collections in the library
`get_collection`	Get details about a specific collection: video count, total duration, storage used
`get_video`	Get metadata and a presigned playback URL for a specific video
`upload_video`	Upload a local video file to a collection for processing. Returns a `job_id`. Available only through the local server because the remote endpoint cannot read your files. Requires a key with write permission
`get_job_status`	Check an indexing job’s status and progress. Poll after `upload_video` until `done`, then the video is searchable

Next steps

Connect an Agent

Per-client setup, config files, and troubleshooting.

Agent Security

Scoping what an agent can do with your library.