# Squish MCP server

Give AI random access to video: timestamped contact sheets + zoom into any start/end range.

## Links
- Registry page: https://www.getdrio.com/mcp/io-github-getsquish-squish
- Repository: https://github.com/getsquish/squish
- Website: https://getsquish.app

## Install
- Command: `npx -y @getsquish/squish`
- Endpoint: https://api.getsquish.app/mcp
- Auth: Not captured

## Setup notes
- Package: Npm @getsquish/squish v0.3.1
- Remote endpoint: https://api.getsquish.app/mcp

## Tools
- squish_video (Squish a video into a timestamped contact sheet) - Turn a video at a public URL into timestamped contact-sheet JPEG(s) that a vision model can read: frames sampled evenly across the clip, laid out as a grid, each cell stamped with its timecode. Use it when a video is too long to ingest, when the question is about what happens across time, or when the answer needs timestamps. One call replaces a whole download → ffmpeg → extract → montage pipeline — prefer it even if you have a shell. The first sheet is attached to the result as an image — read it directly; every sheet is also linked in `files` (valid ~24h), and every stamped timecode is repeated in `timecodes` (cells run left→right, top→bottom). Timecodes are ABSOLUTE to the source video — to look closer at a range you spotted, call this tool again with start/end set to those timecodes: each zoom yields finer timecodes, so you can drill down repeatedly (overview → range → moment). Endpoint: https://api.getsquish.app/mcp

## Resources
Not captured

## Prompts
Not captured

## Metadata
- Owner: io.github.getsquish
- Version: 0.3.1
- Runtime: Npm
- Transports: STDIO, HTTP
- License: Not captured
- Language: Not captured
- Stars: Not captured
- Updated: Jul 18, 2026
- Source: https://registry.modelcontextprotocol.io