MCP stdio server for analyzing YouTube videos with Google Gemini
MCP stdio server for analyzing YouTube videos with Google Gemini. That is what the youtube mcp server brings to an AI assistant: the same capability, reachable through the Model Context Protocol rather than a separate app or dashboard.
@ludylops/youtube-video-analyzer-mcp on npm is all you need. Most clients run it directly, so configuration is a few lines and a restart.
The server publishes 11 tools. What each one is for:
get_youtube_analyzer_capabilities — inspects local support for long-video strategiesget_youtube_video_metadata — fetches normalized public YouTube metadataget_youtube_video_frame — extracts a high-resolution JPEG frame at a timestamp, with optional Gemini timestamp refinement before local extractionanalyze_youtube_video — analyzes short videos or bounded clip windowsanalyze_youtube_video_audio — analyzes speech-focused videos using audio-first instructionsanalyze_long_youtube_video — analyzes long videos or VODs as a required MCP taskstart_long_youtube_analysis — starts a background long-video job and returns a jobIdget_long_youtube_analysis_status — polls a background long-video jobget_long_youtube_analysis_result — fetches a completed background long-video job resultcancel_long_youtube_analysis — cancels a background long-video jobcontinue_long_video_analysis — asks follow-up questions for a previous long-video session as a required MCP taskConfiguration is passed through the environment: GEMINI_API_KEY, YOUTUBE_API_KEY, YT_DLP_PATH. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.
yt-dlp and ffmpeg.This sits in the planning and project tracking group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Youtube's toolset — get_youtube_analyzer_capabilities, get_youtube_video_metadata, get_youtube_video_frame and 8 more — is a fair guide to whether it matches your workflow. It is maintained by ludmila-omlopes; worth a glance at recent repository activity before you build anything load-bearing on it.
We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.
| Tool | What it does |
|---|---|
| get_youtube_analyzer_capabilities | inspects local support for long-video strategies. |
| get_youtube_video_metadata | fetches normalized public YouTube metadata. |
| get_youtube_video_frame | extracts a high-resolution JPEG frame at a timestamp, with optional Gemini timestamp refinement before local extraction. |
| analyze_youtube_video | analyzes short videos or bounded clip windows. |
| analyze_youtube_video_audio | analyzes speech-focused videos using audio-first instructions. |
| analyze_long_youtube_video | analyzes long videos or VODs as a required MCP task. |
| start_long_youtube_analysis | starts a background long-video job and returns a jobId. |
| get_long_youtube_analysis_status | polls a background long-video job. |
| get_long_youtube_analysis_result | fetches a completed background long-video job result. |
| cancel_long_youtube_analysis | cancels a background long-video job. |
| continue_long_video_analysis | asks follow-up questions for a previous long-video session as a required MCP task. |
{
"mcpServers": {
"youtube-analyzer": {
"command": "npx",
"args": ["-y", "@ludylops/youtube-video-analyzer-mcp"],
"env": {
"GEMINI_API_KEY": "your_gemini_key_here",
"YOUTUBE_API_KEY": "optional_youtube_key_here"
}
}
}
}Configuration as documented by the project. Restart the client after saving.
yt-dlp and ffmpeg.| Variable | Description | Required |
|---|---|---|
| GEMINI_API_KEY | Credential the server authenticates with. | Yes |
| YOUTUBE_API_KEY | Credential the server authenticates with. | Yes |
| YT_DLP_PATH | Filesystem location the server is allowed to use. | Optional |
Your workspace, on speaking terms with AI — search, read and write Notion pages and databases.
Issue tracking at the speed of conversation — Linear's official hosted server with OAuth and zero install.
Search and read your Drive — Docs, Sheets and files become context your assistant can actually use.
Your assistant inside the workspace — read channels, search history, post messages and tame the noise.
Metabase ships its own MCP endpoint — search your BI content, build and run queries, and save questions and dashboards without leaving the chat.
Stop letting your assistant hallucinate n8n node parameters — this server hands it the real schemas, templates and validation.