Youtube Video Analyzer
Connects Claude to YouTube videos through Google Gemini's vision and audio models. You get tools to pull metadata via YouTube Data API, extract high-res JPEG frames at specific timestamps with yt-dlp and ffmpeg, and analyze videos with custom prompts. Handles long VODs through MCP tasks or a background job API for clients with fixed timeouts. Supports reusable session IDs for follow-up questions on previously analyzed videos, audio-first analysis for podcasts and interviews, and structured JSON output with custom schemas. Falls back to URL chunking when local download tools aren't available. Requires a Gemini API key and optionally a YouTube API key for metadata lookups.
- GitHub stars
- 2
- tools
- 11
- auth
- Secret needed
- transport
- STDIO
- env vars
- 3
- last updated
- Mar 22, 2026
Tools
11 toolsPublic tool metadata for what this MCP can expose to an agent.
get_youtube_analyzer_capabilitiesinspects local support for long-video strategies.
inspects local support for long-video strategies.
No parameter schema in public metadata yet.
get_youtube_video_metadatafetches normalized public YouTube metadata.
fetches normalized public YouTube metadata.
No parameter schema in public metadata yet.
get_youtube_video_frameextracts a high-resolution JPEG frame at a timestamp, with optional Gemini timestamp refinement before local extraction.
extracts a high-resolution JPEG frame at a timestamp, with optional Gemini timestamp refinement before local extraction.
No parameter schema in public metadata yet.
analyze_youtube_videoanalyzes short videos or bounded clip windows.
analyzes short videos or bounded clip windows.
No parameter schema in public metadata yet.
analyze_youtube_video_audioanalyzes speech-focused videos using audio-first instructions.
analyzes speech-focused videos using audio-first instructions.
No parameter schema in public metadata yet.
analyze_long_youtube_videoanalyzes long videos or VODs as a required MCP task.
analyzes long videos or VODs as a required MCP task.
No parameter schema in public metadata yet.
start_long_youtube_analysisstarts a background long-video job and returns a `jobId`.
starts a background long-video job and returns a `jobId`.
No parameter schema in public metadata yet.
get_long_youtube_analysis_statuspolls a background long-video job.
polls a background long-video job.
No parameter schema in public metadata yet.
get_long_youtube_analysis_resultfetches a completed background long-video job result.
fetches a completed background long-video job result.
No parameter schema in public metadata yet.
cancel_long_youtube_analysiscancels a background long-video job.
cancels a background long-video job.
No parameter schema in public metadata yet.
continue_long_video_analysisasks follow-up questions for a previous long-video session as a required MCP task.
asks follow-up questions for a previous long-video session as a required MCP task.
No parameter schema in public metadata yet.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageConfiguration
GEMINI_API_KEY*secretGoogle Gemini API key.
GEMINI_MODELOptional Gemini model override.
YT_DLP_PATHOptional path to a yt-dlp executable.
Readme
YouTube Video Analyzer MCP
MCP stdio server for analyzing public YouTube videos with Google Gemini.
Use it from any MCP-compatible client to summarize videos, extract timestamped insights, analyze spoken content, inspect metadata, work with long VODs, and ask follow-up questions against reusable long-video sessions.
What It Can Do
- Analyze public YouTube videos with Gemini.
- Analyze speech-focused videos with audio-first instructions.
- Fetch normalized YouTube metadata through the YouTube Data API.
- Extract high-resolution JPEG frames from YouTube videos with
yt-dlpandffmpeg. - Analyze long videos and VODs through required MCP tasks.
- Analyze long videos and VODs through compatibility background jobs for clients without MCP task support.
- Reuse long-video sessions for follow-up questions.
- Fall back to URL chunking when local download tools are unavailable.
- Return structured JSON when you provide a custom response schema.
Requirements
- Node.js 20 or newer.
- A Gemini API key.
- Optional: a YouTube Data API key for metadata lookup.
- Optional for best long-video support:
yt-dlpandffmpeg.
Quick Start
Details
- Repository
- github.com/ludmila-omlopes/youtube-video-analyzer-mcp
- Categories
- AI & LLM Tools, Media & Entertainment
- Package
@ludylops/youtube-video-analyzer-mcp- Transport
- STDIO
- Auth
- Required
- Registry
- MCP registry, active
Related AI & LLM Tools MCP servers
View all
Sentinal Mcpmusaraf-m/sentinalRedis health, BullMQ queue monitoring, memory analysis, and slow query diagnostics2stars
Kernal Mcppintomatic/kernalGraph-native memory for AI agents: a knowledge graph built from conversation, via MCP.2stars
Sprintrasprintra-io/sprintra-mcpThe project brain for AI coding agents — memory, decisions, sprints, knowledge base via MCP.2stars
fmrltoogreatwtf/fmrl-pluginYour agent's outbox. Ask it to publish to fmrl and get a shareable link, no account required.0stars
Redis MCP Serveryawlabs/redis-mcpRead-first Redis MCP: SCAN key explorer, keyspace/TTL/memory/slowlog stats, DBA advisor2stars
Whisper Mcpjwulff/whisper-mcpLocal audio transcription using whisper.cpp. Transcribe with OpenAI Whisper models.2stars