Add VideoDB to your agent
Paste a link or upload a file, then ask. Your agent finds the moment, cuts the clip and sends back a link you can play.
$20 of free credits. No credit card.
Claude on the web, on desktop and on mobile.
- Add VideoDB from the plugin directory. Open VideoDB in Claude.
- Log in or sign up when VideoDB opens, then click Authorize.
- Ask. Paste a link or upload a file and say what you need from it.
To add it by hand, open Settings, then Connectors, then Add custom connector. Paste https://mcp.videodb.io/mcp and click Connect. On Team and Enterprise plans an admin adds it under Organization settings.
The plugin, or the MCP server on its own.
/plugin marketplace add video-db/skills
/plugin install videodb@videodb-skills
/videodb setupTo connect the server directly, run claude mcp add --transport http videodb https://mcp.videodb.io/mcp and then /mcp to authorize.
A global MCP server, used by every project.
- Open Settings, Cursor Settings, MCP, and choose Add new global MCP server.
- Add the server to the configuration:
{
"mcpServers": {
"videodb": { "url": "https://mcp.videodb.io/mcp" }
}
}Cursor opens the VideoDB login on first use.
Codex, Copilot and any agent that loads skills.
npx skills add video-db/skillsThen ask the agent to set up VideoDB. It takes your API key from console.videodb.io.
Any client that speaks MCP over Streamable HTTP.
https://mcp.videodb.io/mcpAdd it as a remote server and log in once. To check that it works, ask the agent to list your VideoDB collections. Steps for each client.
Python and Node, for code you write yourself.
pip install videodb
npm install videodbRead the docs or open the quickstart notebook. Your API key is at console.videodb.io.
What people ask, and what comes back
Every answer comes with the times and frames behind it.
Make chapters and notes for this lecture.
Timestamps, a chapter list and a summary you can paste anywhere.
Find every moment the product is on screen.
The clips, each one playable, with the frames that matched.
Pull every slide from this conference talk.
The slides as images, with the time each one appeared.
Review this match and list the moments to study.
The moments as clips, with a note on each.
Subtitle this video in English, French and German.
Subtitle files in every language, from one transcript.
Find where pricing comes up in these sales calls.
The moments from each call as clips, with what was said around them.
70 tools in six groups
You ask for the result. The agent picks the tools.
The layers underneath| Group | What it covers | Most used |
|---|---|---|
| Bring video in | Files, links, YouTube, buckets, live cameras, screens and microphones. | upload_media connect_rtstream transcode_media |
| Understand it | Describe scenes, transcribe speech, read on-screen text, return your own JSON fields. | understand_video generate_transcript create_index |
| Search it | Plain-language search over one video or a whole collection. | search_video search_collection ask_video |
| Edit it | Clips, timelines, vertical reframing, subtitles, voice and music. | compile_clips reframe_video add_subtitles |
| Stream any result | Every answer as a playable link, for a person or the next tool. | generate_clip render_timeline get_media_download_url |
| Watch live | Connect cameras, set alerts in plain words, get the clip behind each one. | create_rtstream_alert search_rtstream understand_rtstream |
Build your own agent from open code
A repo or a write-up to start from, for each kind of agent.
VideoDB on GitHub- Archive agents
Find, cut and caption moments in games, streams, podcasts and meetings.
Director - Computer-use agents
Capture the screen, understand each step, turn a recording into a skill and keep every run on record.
open-record-replay - Physical agents
Memory for physical devices with cameras: an index of everything seen, and the frames a task needs.
How a robot remembers - Research agents
Search datasets and test runs in plain language, count what is there and export a training set.
datasets.bot - Fleet agents
Find any scenario across every drive, flight and camera, with the time and camera behind each clip.
Scenario search
Questions before you add it
- Is it free to start?
- Yes. New accounts start with free credits and no credit card. After that you pay for storage, processing and search.
- Where do my videos go?
- Into your own VideoDB collection, which only your account and your agents can reach. On your own cloud, the files stay in your bucket. Deleting a video removes it in full.
- Which clients work?
- Claude on web, desktop and mobile, Claude Code, Cursor, and any client that speaks MCP over Streamable HTTP. Python and Node SDKs for code.
- Can it handle long videos?
- Yes. An hour-long recording or a day of camera footage is searched the same way, and the agent reads only the moments it needs.
- Can I bring my own model?
- Yes. Any VLM, speech or detection model runs as an analyzer: open-weight, proprietary or your own.
- Do I need to code?
- No. In Claude you add the plugin and ask. The SDKs and the skills are there when you want to build the agent yourself.
Add VideoDB to Claude
It takes about a minute. Then paste a link or upload a file and ask.