squish
OfficialRelated Servers
Alternatives to squish
FlicenseNot gradedqualityDmaintenanceMCP server enabling video analysis via scene detection, audio transcription, visual description, and stylistic fingerprinting, with tools for full pipeline execution and storyboard generation.-- AlicenseNot gradedqualityDmaintenanceAn MCP server that enables LLMs to analyze video content by extracting frames as base64 images and retrieving video metadata using ffmpeg.15MIT
Related Servers
- AlicenseNot gradedqualityAmaintenanceEnables coding agents to watch and analyze videos by extracting scene-aware frames, transcribing speech, and generating shot timelines, all constrained by a token budget to fit LLM context limits.1MIT
- AlicenseNot gradedqualityDmaintenanceEnables AI assistants to watch YouTube videos by extracting frames at scene changes and visual references, pairing each frame with the exact words spoken at that timestamp. Provides dense frame-transcript interleaving for any model.142MIT
- FlicenseAqualityDmaintenanceExtracts timestamped screenshots from local videos, enabling Claude to produce visual walkthroughs without audio analysis or cloud processing.4-
- AlicenseNot gradedqualityAmaintenanceExtracts ffprobe metadata, subtitles, scenes, and timelines from video files without frame-by-frame LLM vision, providing evidence-first reading for AI agents.133MIT

ilinxa-captureofficial
AlicenseNot gradedqualityAmaintenanceEnables AI agents to extract video frames at configurable FPS and compose them into grid sheets for multimodal LLMs, with support for video download, HLS streams, and job management via MCP tools.2Apache 2.0- AlicenseNot gradedqualityBmaintenanceSearch within videos by dialogue, on-screen visuals, and recurring faces using natural language - connected with your favorite agent (like Claude, Codex, Hermes).51MIT
TDQS
Scored across 1 tool
There is only one tool, so there is no overlap or ambiguity to confuse an agent. `squish_video` is clearly the single, distinct operation the server provides.
The single tool name `squish_video` follows a clear verb_noun pattern and matches the server name. There are no mixed conventions or conflicting styles.
One tool is on the low side compared to typical MCP servers, but the tool itself is substantial and self-contained: it supports overview, zooming, timestamps, and audio activity in one call. The count is slightly thin but reasonable for this focused purpose.
The tool covers the main video-to-contact-sheet workflow completely, including repeated drill-down into time ranges. The only real boundary is that it does not transcribe or classify audio content, so agents needing speech-level detail would need an external tool.