Vidin
Turn a screen recording into agent-readable annotated keyframes.
Connector by teunlao · GitHub account verified by the MCP Registry
Install
Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.
npx agentmarket install connector/teunlao-vidin
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this server can do and what it asks for, from its tool list, install config and code. Checked Oct 25, 2026.
- Tools
- 2 read · 0 write · 0 delete · 2 not yet classified
- Secrets
- None asked for
- Install scripts
- None found
- Runs as
- Node.js package
Tools by what they do 4
Read from the source code; the running server may list different tools.
Read 2 · Look things up without changing anything.
analyze_videoget_frames
Not yet classified 2 · We could not tell from the name and description.
probe_videozoom_clip
Network hosts it talks to 1
github.com· found in code
Files it touches
/usr/share/fonts/truetype/dejavu/DejaVuSansMono.ttf/usr/share/fonts/truetype/liberation/LiberationMono-Regular.ttf/usr/share/fonts/TTF/DejaVuSansMono.ttf- Any path the agent passes to its tools
Tools (4)
Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].
analyze_videoAnalyze a video into keyframesTurn a video file or URL into a set of annotated keyframes plus a written report. Frames are chosen adaptively: one is kept each time the screen changes and then settles, so a long recording of someone reading costs almost nothing while every real UI event is captured. Mouse movement alone never spends a frame. Each frame is annotated with a red dashed box around what changed and a timestamp bar. Returns the report text and one contact sheet image showing the whole video at a glance; open individual frame files (or call get_frames) only for the moments that matter.
get_framesRead specific frames from an analysed videoReturn full-detail frames from a session created by analyze_video, as images. Select them by frame number (as listed in REPORT.md) or by a time range. Use this after reading the report instead of opening every frame: each frame costs roughly 1.5k vision tokens.
probe_videoRead video metadataDuration, resolution, frame rate, codec and whether the file has an audio track. Cheap — use it to decide on a profile before analysing a long recording.
zoom_clipRe-extract a short window at a high frame rateDensely sample a narrow time window of the original video — use it when two keyframes are not enough to tell what happened between them (a flash, a transient error, the exact moment a click landed). Keep the window short: frames are returned at the requested fps.
Compare and alternatives
Featured in
Signals
- Stars
- 2
- Forks
- 0
- Open issues
- 0
- Last commit
- Oct 15, 2026 (13 days ago)
- Last release
- Jul 31, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- Registry name
io.github.teunlao/vidin- Version
- 0.1.0
- Auth
- No auth
- Packages
- npm @teunlao/vidin
- License
- MIT
- Repository
- github.com/teunlao/vidin
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
Cite this page
Vidin MCP server. Agent Mart. https://agentmart.dev/connectors/teunlao-vidin (last updated 2026-10-24)