vidlens-mcp — Claude Code MCP server: what it does, how to install
Connects AI agents to video analysis across YouTube, social platforms, and local disks. It extracts transcripts, inspects frames, and tracks precise timestamps.
claude mcp add vidlens-mcp -e YOUTUBE_API_KEY=<YOUTUBE_API_KEY> -e GEMINI_API_KEY=<GEMINI_API_KEY> -e OPENAI_API_KEY=<OPENAI_API_KEY> -e SCRAPECREATORS_API_KEY=<SCRAPECREATORS_API_KEY> -e BRAVE_API_KEY=<BRAVE_API_KEY> -- npx -y vidlens-mcpWhat vidlens-mcp does
This server equips your coding agent with 47 tools to inspect YouTube uploads and local video files. It transcribes audio, extracts on-screen text with OCR, and indexes individual frames. Everything lands in a single folder on your hard drive. Because assets remain cached locally, your assistant never has to process the same clip twice.
Basic YouTube queries and transcripts work without any API keys. The server relies on fallbacks like yt-dlp or page scraping whenever official access fails. Every response reports its data route. However, you will need valid credentials such as GEMINI_API_KEY or OPENAI_API_KEY if you opt into the enhanced setup.
When tracking specific charts or slides, searchVisualContent opens extracted frames directly in your web browser. No external database or Docker is required. Managing backups is as simple as copying the folder.
What it helps with
- locate exact timestamps and frames across long video recordings
- summarize consensus and disagreements across multiple video reviews
- transcribe spoken audio without mandatory paid API subscriptions
- detect on-screen charts and slides using visual OCR search
Example prompts for the agent
- Search YouTube for recent device reviews and compare reviewer conclusions
- Transcribe this public video clip and extract the key takeaways
- Find the frame in this video where the benchmark graph is shown
How to install vidlens-mcp
Platform CLI
claude mcp add vidlens-mcp -e YOUTUBE_API_KEY=<YOUTUBE_API_KEY> -e GEMINI_API_KEY=<GEMINI_API_KEY> -e OPENAI_API_KEY=<OPENAI_API_KEY> -e SCRAPECREATORS_API_KEY=<SCRAPECREATORS_API_KEY> -e BRAVE_API_KEY=<BRAVE_API_KEY> -- npx -y vidlens-mcpReplace <…> with your own values
Platform CLI
codex mcp add vidlens-mcp --env YOUTUBE_API_KEY=<YOUTUBE_API_KEY> --env GEMINI_API_KEY=<GEMINI_API_KEY> --env OPENAI_API_KEY=<OPENAI_API_KEY> --env SCRAPECREATORS_API_KEY=<SCRAPECREATORS_API_KEY> --env BRAVE_API_KEY=<BRAVE_API_KEY> -- npx -y vidlens-mcpReplace <…> with your own values
Config file
{
"mcpServers": {
"vidlens-mcp": {
"command": "npx",
"args": [
"-y",
"vidlens-mcp"
],
"env": {
"YOUTUBE_API_KEY": "<YOUTUBE_API_KEY>",
"GEMINI_API_KEY": "<GEMINI_API_KEY>",
"OPENAI_API_KEY": "<OPENAI_API_KEY>",
"SCRAPECREATORS_API_KEY": "<SCRAPECREATORS_API_KEY>",
"BRAVE_API_KEY": "<BRAVE_API_KEY>"
}
}
}
}Replace <…> with your own values
Config file
{
"servers": {
"vidlens-mcp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"vidlens-mcp"
],
"env": {
"YOUTUBE_API_KEY": "<YOUTUBE_API_KEY>",
"GEMINI_API_KEY": "<GEMINI_API_KEY>",
"OPENAI_API_KEY": "<OPENAI_API_KEY>",
"SCRAPECREATORS_API_KEY": "<SCRAPECREATORS_API_KEY>",
"BRAVE_API_KEY": "<BRAVE_API_KEY>"
}
}
}
}Replace <…> with your own values
Platform CLI
gemini mcp add -e YOUTUBE_API_KEY=<YOUTUBE_API_KEY> -e GEMINI_API_KEY=<GEMINI_API_KEY> -e OPENAI_API_KEY=<OPENAI_API_KEY> -e SCRAPECREATORS_API_KEY=<SCRAPECREATORS_API_KEY> -e BRAVE_API_KEY=<BRAVE_API_KEY> vidlens-mcp npx -y vidlens-mcpReplace <…> with your own values
Step by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more
Questions about vidlens-mcp
How to install vidlens-mcp in Claude Code?
Run `claude mcp add vidlens-mcp -e YOUTUBE_API_KEY=<YOUTUBE_API_KEY> -e GEMINI_API_KEY=<GEMINI_API_KEY> -e OPENAI_API_KEY=<OPENAI_API_KEY> -e SCRAPECREATORS_API_KEY=<SCRAPECREATORS_API_KEY> -e BRAVE_API_KEY=<BRAVE_API_KEY> -- npx -y vidlens-mcp` in your terminal. Then restart your client session to load the server.
What does vidlens-mcp do?
It allows AI agents to inspect and search videos by transcribing speech, indexing on-screen visual elements, and running OCR. The server caches everything on your machine, eliminating redundant downloads for subsequent queries.
Are API keys required to use vidlens-mcp?
No, basic YouTube search, transcripts, and the local library function without any keys. Extra credentials like GEMINI_API_KEY or OPENAI_API_KEY are only needed if you choose the enhanced setup for third-party speech services.
