vidlens-mcp

🔍 What is VidLens?

Stop watching 10 videos to answer one question. VidLens searches YouTube, reads the transcripts, and synthesizes what creators actually said — across multiple videos, with timestamps, benchmark charts, and sources.

VidLens is a Model Context Protocol server that gives AI agents deep, reliable access to YouTube. Not just transcripts — full intelligence: search, analysis, visual search, and auto-generated comparison charts.

No API key required to start. Every tool has a three-tier fallback chain (YouTube API → yt-dlp → page extraction) so nothing breaks when quota runs out or keys aren't configured.

Try it — paste any of these into Claude:

"I'm thinking about buying the M5 Max MacBook Pro. Search YouTube for top tech reviewers and tell me what they're saying. Is it worth the upgrade from M3/M4?"

VidLens finds 10+ reviews, reads the transcripts, extracts benchmark scores, and presents comparison charts — all from one prompt.

"I want to understand how AI agents work. Search YouTube for the best videos for a beginner and summarize what I need to know."

Discovers videos across creators, ranks by learning value, and prepares transcripts for follow-up questions.

"Search YouTube for reviews comparing the iPhone 17 Pro vs Samsung S26 Ultra. What do reviewers agree on? Where do they disagree?"

Searches, reads transcripts from multiple reviewers, and synthesizes consensus vs disagreements with sources.

🎯 Core Capabilities

🔍 Explore — One Prompt, Full Pipeline

Ask a question about YouTube and VidLens does the rest: searches, ranks by creator match and freshness, reads transcripts, extracts benchmark data, and presents comparison charts automatically. Works for product research, learning, competitive analysis — anything on YouTube.

🔎 Semantic Search Across Playlists

Import entire playlists or video sets, index every transcript with Gemini embeddings, and search across hundreds of hours of content by meaning — not just keywords.

👁️ Visual Search — See What's In Videos

Extract keyframes, describe them with Gemini Vision, run OCR on slides and whiteboards, and search by what you see — not just what's said.

📊 Intelligence Layer — Not Just Data

Sentiment analysis, niche trend discovery, content gap detection, hook pattern analysis, upload timing recommendations. The LLM does the thinking — VidLens gives it the right data.

⚡ Zero Config, Always Works

No API key needed to start. Three-tier fallback chain on every tool. Nothing breaks when quota runs out. Keys are optional power-ups.

🎬 Full Media Pipeline

Download videos/audio/thumbnails. Extract keyframes. Index comments for semantic search. Build a local knowledge base from any YouTube content.

⚡ Why VidLens?

🚀 Quick Start

1. Install

npx vidlens-mcp setup

This auto-detects your MCP clients (Claude Desktop, Claude Code), downloads yt-dlp if needed, and configures everything. No manual setup required.

2. Or configure manually

Claude Desktop — add to ~/Library/Application Support/Claude/claude_desktop_config.json:

{
  "mcpServers": {
    "vidlens-mcp": {
      "command": "npx",
      "args": ["-y", "vidlens-mcp", "serve"]
    }
  }
}

Claude Code — add to ~/.claude/settings.json:

{
  "mcpServers": {
    "vidlens-mcp": {
      "command": "npx",
      "args": ["-y", "vidlens-mcp", "serve"]
    }
  }
}

3. Restart your MCP client

Fully quit and reopen Claude Desktop (⌘Q). Claude Code picks up changes automatically.

4. Try it

Start with "Search YouTube" to activate VidLens:

"Search YouTube for the top M5 Max MacBook Pro reviews and tell me if it's worth upgrading from M4."

"Search YouTube for the best videos about agentic AI for a beginner."

"Import this playlist and search across all videos for mentions of machine learning."

"Search this video's frames for the benchmark comparison chart."

"What's trending in the AI coding niche right now?"

🧰 Tools - 41 across 10 modules

🔍 Explore - YouTube Discovery & Research

The front door — one prompt, full pipeline

📺 Core - Video & Channel Intelligence

Always available, no API key needed

🔎 Knowledge Base - Semantic Search

Index transcripts and search across them with natural language

💬 Sentiment & Analysis

Understand what audiences think and feel

🎯 Creator Intelligence

Insights for content strategy

📈 Discovery & Trends

Find what's working in any niche

🎬 Media Assets

Download and manage video files locally

🖼️ Visual Search

Three-layer visual intelligence. Not transcript reuse.

Three layers, all real:

1. Apple Vision feature prints — image-to-image similarity (find frames that look alike)
2. Gemini 2.5 Flash frame descriptions — natural language scene understanding per frame
3. Gemini semantic embeddings — 768-dim embedding retrieval over OCR + description text for true text→visual search

What you always get back: frame path on disk, timestamp, source video URL/title, match explanation, OCR text, visual description.

What is NOT happening: no transcript embeddings are reused for visual search. This is a separate visual index.

💭 Comment Knowledge Base

Index and semantically search YouTube comments

🏥 Diagnostics

Health checks and pre-flight validation

🔑 API Keys (Optional)

VidLens works without any API keys. Add them to unlock more capabilities:

⚠️ These are separate keys from separate Google services. A Gemini key will NOT work for YouTube API calls and vice versa. Create them independently.

# Configure via setup wizard
npx vidlens-mcp setup --youtube-api-key YOUR_YOUTUBE_KEY --gemini-api-key YOUR_GEMINI_KEY

# Or via environment variables
export YOUTUBE_API_KEY=your_youtube_key
export GEMINI_API_KEY=your_gemini_key

💻 CLI

npx vidlens-mcp               # Start MCP server (stdio)
npx vidlens-mcp serve         # Start MCP server (explicit)
npx vidlens-mcp setup         # Auto-configure Claude Desktop + Claude Code
npx vidlens-mcp doctor        # Run diagnostics
npx vidlens-mcp version       # Print version
npx vidlens-mcp help          # Usage guide

Doctor - diagnose issues

npx vidlens-mcp doctor --no-live

Checks: Node.js version, yt-dlp availability, API key validation, data directory health, MCP client registration (Claude Desktop, Claude Code).

📱 Works Everywhere — Desktop, Cowork, Phone

VidLens works across the full Claude ecosystem. Set it up once, use it everywhere.

Claude Desktop — Chat

The classic experience. Ask a question, get charts and analysis inline. Best for interactive research sessions.

Claude Desktop — Cowork Projects (March 2026)

Create a persistent research project with VidLens connected. Claude remembers context across sessions — last week's competitive research informs this week's analysis. Set up scheduled tasks that run automatically:

"Every Monday, search YouTube for new AI agent framework videos and compare to last week's findings."

Claude Dispatch — From Your Phone (March 2026)

Trigger any VidLens research from the Claude mobile app. Ask from your phone, Claude Desktop runs the tools locally, results come back to your pocket:

"Run my competitive research project — what new M5 Max content dropped this weekend?"

Claude Code — Remote Control

Start a Claude Code session with claude --remote-control, then continue from any browser or your phone at claude.ai/code. Full tool access, full context.

Note: Your Mac must be awake with Claude Desktop open for Cowork, Dispatch, and scheduled tasks to execute.

🏗️ Architecture

System Overview

How the Fallback Chain Works

Every tool that touches YouTube data uses the same resilience pattern:

Every response includes a provenance field telling you exactly which tier served the data and whether anything was partial. No silent degradation — you always know what happened.

Visual Search Pipeline

Visual search is not transcript reuse. It's a dedicated three-layer index:

Three layers, all real:

1. Apple Vision feature prints — image-to-image similarity (find frames that look alike)
2. Gemini Vision frame descriptions — natural language scene understanding per frame
3. Gemini semantic embeddings — 768-dim retrieval over OCR + description text

Data Storage

Everything lives in a single directory. No external databases, no Docker, no infrastructure.

One directory. Portable. Back it up by copying. Delete it to start fresh.

📋 Requirements

🔧 Troubleshooting

"Tool not found" in Claude Desktop

Fully quit Claude Desktop (⌘Q, not just close window) and reopen. MCP servers only load on startup.

"YOUTUBE_API_KEY not configured" warning

This is informational, not an error. VidLens works without it. Add a key only if you need comments/sentiment features.

"API_KEY_SERVICE_BLOCKED" error

Your API key has restrictions. Create a new unrestricted key in Google Cloud Console, or remove the API restriction from the existing key.

Gemini key doesn't work for YouTube API

These are separate services. You need a YouTube API key from Google Cloud Console AND a Gemini key from Google AI Studio. They are not interchangeable.

Build errors

npx vidlens-mcp doctor     # Run diagnostics
npx vidlens-mcp doctor --no-live  # Skip network checks

📄 License

MIT

GitHub · npm · Model Context Protocol