Squish
Server Details
Give AI random access to video: timestamped contact sheets + zoom into any start/end range.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- Repository
- getsquish/squish
- GitHub Stars
- 2
- Server Listing
- squish
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 1 tool
With a single tool there is no sibling tool to confuse it with, so misselection is structurally impossible. The description further clarifies when to prefer it (long videos, temporal questions, timestamped answers) and how repeated drill-down calls differ from the first overview call.
The lone name `squish_video` is lowercase snake_case with a domain noun, which is readable and predictable. A single name means no cross-tool pattern can actually be verified, so it falls just short of a 5.
One tool is defensible here because the server has a narrow, well-defined job: video URL to timestamped contact sheets. Zoom/range behavior is folded into `start`/`end` parameters rather than duplicated as extra tools, though a single entry point leaves no room for adjacent operations like raw frame extraction.
The core lifecycle is covered: an overview pass, iterative drill-down via absolute timecodes, image attachment plus `files` links and a `timecodes` array for downstream parsing. Gaps are peripheral — no audio/transcript handling, no video metadata probe, and no direct single-frame grab for pinpoint precision.
Available Tools
1 toolsquish_videoSquish a video into a timestamped contact sheetAInspect
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. 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).
Inputs: end, start, video, density, +1 more. Returns: files, input, frames, job_id, +11 more
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Video analysis AI: transcripts, summaries, visual scenes/shots, clips, answers in natural language.
YouTube frames at exact timestamps and the moments that answer a query, for AI agents.
VideoDB lets an AI agent watch, search and clip video.
Shot breakdowns of video clips, plus logos and brand kits, for any AI assistant.
Related MCP Servers
- AlicenseAqualityBmaintenanceEnables AI agents to index videos locally once and then browse a compact text map of shots, transcript, silences and visual embeddings, so they can query moments, cut dead air, apply edit scripts, render with ffmpeg and run QA checks without spending tokens on frames. Pixels are only fetched when the agent explicitly peeks at labeled contact sheets.9MIT
- AlicenseNot gradedqualityBmaintenanceEnables coding agents to search and interrogate video by screening labelled contact sheets with typed decision-model questions, returning timed hits with probabilities, full-resolution frames and nearby dialogue without building any vector index. Agents can find specific moments, verify them, zoom into frames, box objects, and map an entire film.25 PyPI55MIT
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to inspect UI screen recordings as token-efficient image sheets with changed regions boxed, single-frame flicker flagged, and speech aligned to frames. Exposes watch_video and zoom_video tools so agents can pull dense keyframes across any time range or one sharp full-resolution frame, all processed locally.23 npmMIT
- FlicenseNot gradedqualityBmaintenanceEnables AI clients to watch and hear videos from local files or YouTube, Vimeo, and Loom links by returning timestamped key frames, a transcript, a contact sheet, and a combined timeline, with all processing done locally.-
Glama MCP Gateway
Add one secure layer between your agents and this server.