mcp server
Squish
Give AI random access to video: timestamped contact sheets + zoom into any start/end range.
Description as published by the maintainer. Source
- version 0.3.1
- active
active — Most recent push to the repository was 2026-07-18.
What this server can do
1 function, named and described by the server itself. Parameter names are shown because they say more about what a function does than its name usually does.
squish_video(end, start, video, density, video_url)- 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).
Last successful function declaration observed on . Source: https://api.getsquish.app/mcp. We list what the server declared; we do not call any of these functions.
Endpoint status observed on . Source: https://api.getsquish.app/mcp.
Signals
These are separate measurements of different things. They are deliberately not combined into one score, because a popularity number that mixes website traffic with saves and stars cannot be checked or acted on.
| Signal | Value | What it measures | Window | Observed | Source |
|---|---|---|---|---|---|
| GitHub stars | 1 | Number of GitHub accounts that bookmarked this repository since it was created. It is a bookmark count, not installs, not active users and not quality. | cumulative, all time | GitHub | |
| Last commit | 2026-07-18 | Date of the most recent push to any branch. This is the strongest cheap indicator of whether the project is still maintained. | point in time | GitHub | |
| Open issues | 1 | Open issues plus open pull requests, as GitHub counts them together. A high number can mean an active project or an abandoned one. | as of fetch | GitHub | |
| Latest published version | 0.3.1 | Latest version string the maintainer published to the registry. | as of fetch | Model Context Protocol | |
| Registry record last updated | 2026-07-18 | When the registry record was last updated by its maintainer. | point in time | Model Context Protocol | |
| License | Apache-2.0 | Licence GitHub detected in the repository. Detection can be wrong; the LICENSE file is authoritative. | as of fetch | GitHub | |
| First listed in the MCP Registry | 2026-07-18 | Date this server was first published to the official MCP Registry. Not a usage or quality measure. | point in time | Model Context Protocol | |
| repository status | active | The repository exists on GitHub and is not archived. This says nothing about how recently it was worked on. | as of fetch | GitHub | |
| mcp tools declared | 1 tools | Number of functions the server itself declared when asked to list them. This is what the server offers an agent, not a measure of how well any of them work. | as of probe | api.getsquish.app | |
| mcp endpoint status | ok | The server listed 1 function when asked. | as of probe | api.getsquish.app |
Where to get it
Related, by what their authors tagged them
-
ai.primateintelligence/mcp
— last commit 2026-08-01, shares video-analysis
Video scene understanding for AI agents via the Primate Vision API.
-
Contendeo
— last commit 2026-04-24, shares video-analysis
Multimodal video analysis MCP — transcription, vision, and OCR for any video URL.
-
app.uploadcheck/uploadcheck
— last commit 2026-07-23, shares ffmpeg, video
QC videos, podcasts, and clips before upload — timestamped flags with agent-ready repair prompts.
-
com.ffmpeg-micro/mcp-server
— last commit 2026-04-30, shares ffmpeg, video
MCP server for the FFmpeg Micro video transcoding API — create, monitor, download transcodes.
-
Rendobar
— last commit 2026-08-06, shares ffmpeg, video
Transform video, audio and images, and generate media from prompts. FFmpeg, captions, models.
-
io.github.bytedance/mcp-server-browser
— last commit 2026-08-05, shares vision
MCP server for browser use access
-
io.github.bytedance/mcp-server-commands
— last commit 2026-08-05, shares vision
An MCP server to run arbitrary commands
-
io.github.bytedance/mcp-server-filesystem
— last commit 2026-08-05, shares vision
MCP server for filesystem access
-
io.github.bytedance/mcp-server-search
— last commit 2026-08-05, shares vision
MCP server for web search operations
-
Optical Context MCP
— last commit 2026-04-04, shares vision
Compress OCR-heavy PDFs into dense packed images so agents can work with long visual documents.
These share tags the maintainers applied themselves, such as video-analysis, ffmpeg, video, vision. Common tags like "mcp" or "ai" are ignored for this: agreeing with six hundred other projects is not a similarity.
This is not a recommendation and not a test result. It is a map of what the authors said their work is about.
How the author describes it
Topics the maintainer set on GitHub: ai, ai-agents, contact-sheet, ffmpeg, mcp, video, video-analysis, vision.
This record as data
Every field on this page, with its source and observation date, is in the catalog JSON. Fetch the whole kind at once instead of parsing this HTML.
GET /api/v1/entries/mcp_server.json