A
licenseA
qualityC
maintenanceEnables AI agents to extract, analyze, and manipulate images, PDFs, video, and audio while conserving context through downscaling, truncation, and frame/page caps.
22
MIT
KEEP Highlights
by Volgat
Click on "Deploy 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., "@KEEP Highlightsfind highlights in my vacation video"
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.
KEEP Highlights — Claude & OpenAI MCP Connector
Official open-source Model Context Protocol (MCP) connector for KEEP Highlights — the intelligent multimodal media time compression and highlight engine.
🚀 Quickstart for Claude Desktop
1-Click Install with Smithery:
npx -y @smithery/cli install @skeepit/keep-mcp --client claudeOr Manual Install in Claude Desktop:
Add to your claude_desktop_config.json:
{
"mcpServers": {
"keep-highlights": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://api.skeepit.co/mcp"]
}
}
}Related MCP server: mcp-video-frames
🛠️ Tools Included
discover_highlights: Multimodal acoustic & visual surprise analysis with timestamp intervals.condense_media: Lossless stream temporal squeezing and media assembly (-c copy).
🌐 Links
Website: https://skeepit.co
Developer Gateway: https://api.skeepit.co
Privacy Policy: https://skeepit.co/privacy.html
This server cannot be deployed
Maintenance
ActivityMaintained
ResponsivenessNo issues
Related MCP Connectors
Video, audio, and image processing for AI agents: convert, transcribe, upscale - 150+ operations.
Video pipeline for AI agents: analyze with AI, transcode to MP4/HLS/DASH, edit, protect and deliver.
Transcribe, subtitle, dub and lip-sync media; create speech, voices, images and thumbnails.
Video editing for AI agents: cuts, captions, audio, motion graphics, previews, and exports.
Related MCP Servers
- AlicenseAqualityAmaintenanceEnables image-only models to view videos as timestamped frames and retrieve measurable video properties such as scene cuts, silences, and loudness.24MIT
- FlicenseNot gradedqualityNot gradedmaintenanceEnables agents to ingest local video files or URLs, analyze footage for mood, energy, speech, and scene cuts, and receive license-labeled royalty-free or Creative Commons BGM shortlists with a 12–20s hook window, beat-snapped cut suggestions, and an ffmpeg ducking/mix spec.-
- FlicenseNot gradedqualityAmaintenanceEnables agents to analyze video footage for scene, mood, speech, and BPM cues, then recommend license-safe BGM with hook windows and generate ffmpeg ducking and mix specs.-