Agents & MCP
Give your agent
eyes on video.
Video Context is built for agents first. Connect the MCP server, and your agent can understand, search, segment, and edit video as tool calls.
1. Onboard with one line
Paste this into Claude Code, Cursor, Codex, or any coding agent.
Use curl to read https://videocontextapi.com/agents.md, then follow it to set up Video Context for me.
2. Connect the MCP server
The MCP server is open to beta partners. After your beta call, we send you the server address and a beta key. You add them to Claude, ChatGPT, Gemini, Cursor, or any MCP client.
Tools your agent gets
understand_video
Index a video from a URL and return its context: scenes, shots, transcript, on-screen text, objects, and summary.
search_moments
Search one video or a whole index in natural language. Returns moments with start, end, and confidence.
query_segments
Filter the segments of a catalog by type, labels, objects, speakers, and time.
create_edit
Give an editing tool the context for a goal in plain language: scenes, pauses, speakers, and key moments, as timeline JSON.
extract_template
Turn a video into a reusable template of sections, timing, and slots.
extract_style
Measure the style of a video: pacing, cut rhythm, captions, colour, and framing.
FAQ
Questions, answered.
How agents use Video Context.
Does Video Context have an MCP server?+
Yes. The Video Context MCP server gives agents tools to understand, search, segment, edit, template, and style video. Beta partners get access after a short call. See https://videocontextapi.com/mcp/ for the setup.
Which agents work with Video Context?+
Any MCP client: Claude Code, Claude Desktop, Cursor, Codex, VS Code, Windsurf, and others. Agents without MCP can call the REST API.
Can my agent set up Video Context by itself?+
Yes. Paste this into your agent: "Use curl to read https://videocontextapi.com/agents.md, then follow it to set up Video Context for me." The agent reads the guide, explains the options, and helps you book beta access.
Your videos contain
valuable data.
Start using it.
Analyse video at scale. Find exactly what you need. Give your products and AI the context to act on it.