{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_qatearse5kur","handle":"videoscan-mcp","url":"https://wellknown.network/agents/videoscan-mcp","links":{"self":"https://wellknown.network/agents/videoscan-mcp/record.json","html":"https://wellknown.network/agents/videoscan-mcp","markdown":"https://wellknown.network/agents/videoscan-mcp/record.md","api":"https://wellknown.network/api/v1/agents/videoscan-mcp","status":"https://wellknown.network/api/v1/agents/videoscan-mcp/status","claim":"https://wellknown.network/agents/videoscan-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/videoscan-mcp/claim.json","badge":"https://wellknown.network/agents/videoscan-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/videoscan-mcp/history","tools":"https://wellknown.network/api/v1/agents/videoscan-mcp/tools"},"ard":{"identifier":"urn:air::server:videoscan-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"videoscan-mcp","summary":"MCP server for comprehensive video analysis — transcription, AI-powered visual frame analysis, and metadata extraction","description":"# VideoScan MCP\n\nAn MCP (Model Context Protocol) server for comprehensive video analysis — AI-powered transcription, visual frame analysis, and metadata extraction from 1000+ platforms.\n\n## Features\n\n- **Full video analysis** — combines transcription, frame extraction, and metadata in a single call\n- **AI vision analysis** — describes frames and extracts on-screen text (OCR) using GPT-4o, Claude, or Gemini\n- **Audio transcription** — Whisper-based transcription with timestamps and language detection\n- **Auto-tuning** — automatically adjusts frame extraction density, interval, and detail level based on video duration\n- **Smart frame extraction** — scene-change detection, interval sampling, or combined strategy\n- **Deduplication** — perceptual hashing removes near-duplicate frames before analysis\n- **Metadata extraction** — title, duration, chapters, tags, view count, and more without full download\n- **Multi-provider** — OpenAI, Anthropic, and Google vision providers with per-request override\n- **Caching** — persistent cache for downloads, frames, and results to minimize repeat costs\n- **1000+ platforms** — powered by yt-dlp (YouTube, Vimeo, Twitter/X, TikTok, and more)\n\n## Installation\n\n```bash\npip install videoscan-mcp\n```\n\n### System dependencies\n\nVideoScan requires [ffmpeg](https://ffmpeg.org/download.html) for video processing and [yt-dlp](https://github.com/yt-dlp/yt-dlp) for downloading from URLs.\n\n```bash\n# macOS\nbrew install ffmpeg yt-dlp\n\n# Ubuntu/Debian\napt install ffmpeg\npip install yt-dlp\n\n# Windows — install ffmpeg from https://ffmpeg.org/download.html, then:\npip install yt-dlp\n```\n\n## Configuration\n\nCopy `.env.example` to `.env` and fill in at minimum one API key:\n\n```env\n# Vision provider (frame analysis)\nVISION_PROVIDER=openai          # openai | anthropic | google\nVISION_MODEL=                   # optional — defaults: gpt-4o / claude-sonnet-4-20250514 / gemini-2.0-flash\n\n# Transcription provider\nTRANSCRIPTION_PROVIDER=openai   # openai only for now\n…","publisher":{"name":"Lee","url":null},"homepage":null,"repository":null,"version":"0.1.4","license":null,"protocols":["mcp"],"tags":["ai","analysis","mcp","transcription","video","vision"],"pricing":null,"endpoints":[{"url":"pypi:videoscan-mcp","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","summary":"pypi","version":"pypi","description":"pypi","publisherName":"pypi"}},"derived":{"capabilities":[{"slug":"media.image-understanding","name":"Image Understanding","confidence":1,"provenance":"declared"},{"slug":"media.speech-recognition","name":"Speech Recognition","confidence":1,"provenance":"declared"},{"slug":"content.social","name":"Social Media","confidence":0.791,"provenance":"derived"}],"categories":["content","media"],"language":"en"},"observed":{"status":"unknown","statusReason":"Distributed as a package to run locally; no network endpoint to check.","lastOkAt":null,"lastProbedAt":null,"statusComputedAt":null,"reliability30d":null,"latestObservations":[],"tools":null,"package":{"name":"videoscan-mcp","registry":"pypi","observedAt":"2026-10-22T23:26:14.036Z","publishedAt":"2026-03-26T20:22:41.984833Z","latestVersion":"0.1.4"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"videoscan-mcp","url":"https://pypi.org/project/videoscan-mcp/","firstSeenAt":"2026-09-10T15:23:35.345Z","fetchedAt":"2026-10-22T23:24:36.270Z","normalizedAt":"2026-10-22T23:24:36.270Z"}]},"firstSeenAt":"2026-09-10T15:23:35.345Z","updatedAt":"2026-10-22T23:26:14.036Z"}