Extracts key frames from Loom videos for debugging analysis, automatically detecting scene changes and providing visual snapshots of video content.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Loom Local MCP Serveranalyze this Loom video for debugging: https://loom.com/share/xyz789"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Loom Local MCP Server
MCP server for extracting key frames from Loom videos or local files for debugging analysis.
Quick Start
# Build and start the container
./scripts/setup.shUsage
Claude Code Configuration
Add to ~/.claude.json:
{
"mcpServers": {
"loom-agent": {
"command": "docker",
"args": ["exec", "-i", "loom-agent", "python", "-m", "loom_agent"]
}
}
}Analyzing Loom Videos
In Claude Code, simply mention a Loom URL:
"I'm debugging this issue in auth.py. Here's the Loom showing the bug: https://loom.com/share/abc123"
Claude will automatically extract key frames and analyze them.
Local Video Files
Drop video in
~/loom-videos/Reference by filename:
"Check out the bug in this recording: bug-demo.mp4"
Tool Parameters
Parameter | Default | Description |
| required | Loom URL or local filename |
| 0.3 | Scene change sensitivity (0.0-1.0). Lower = more frames |
| 20 | Maximum frames to extract |
Directories
~/loom-videos/- Drop local videos here~/loom-frames/- Extracted frames appear here
Development
# Install dev dependencies
pip install -e ".[dev]"
# Run tests
pytest
# Run server locally (without Docker)
python -m loom_agent