What it does
vidin converts a screen recording into a set of annotated keyframes, presented in a form that agents can read. It is available both as an MCP server and as a command-line tool. Someone might reach for it when they want an agent to work from a recorded screen session rather than from video directly.
The publisher describes it as built on ffmpeg, so ffmpeg is the underlying media tool it relies on. The source material gives no further details on setup or usage; the project's repository is the place to find them.
Limitations and requirements
Built on ffmpeg, so ffmpeg must be available for the tool to process recordings. The source states no other requirements.
Safety
Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.
- Runs code or changes an assistant's behaviour
Sources
- Official MCP Registry first seen 13 Nov 2026 · last seen 13 Nov 2026 · its page on the source
io.github.teunlao/vidin
Turn a screen recording into agent-readable annotated keyframes. MCP server + CLI on ffmpeg.
v0.1.0As shown on registry.modelcontextprotocol.io when we last read it