Analyzes YouTube channels and videos to produce structured intelligence reports.
Accepts a YouTube channel URL, @handle, channel ID, or legacy URL, plus optional max_videos (default 5, max 50).
Fetches recent videos, extracts transcripts, and counts videos analyzed vs transcripts available.
Performs keyword frequency analysis across all transcripts to identify top topics.
If GEMINI_API_KEY is set, produces per-video semantic analysis with theme, named entities, and tags (topics_structured); otherwise falls back to keyword-only mode.
Returns a JSON report with channel metadata, sample video IDs, topics, analysis mode note, and optional output path to a local artifact file.
Requires YOUTUBE_API_KEY and APIFY_TOKEN; GEMINI_API_KEY is optional.
Extracts structured intelligence from YouTube channels, including transcript extraction, topic frequency analysis, competitive signal detection, and content positioning analysis.
MCP server for extracting structured intelligence from YouTube channels and videos.
Analyzes YouTube channels to produce structured intelligence reports:
Transcript extraction across recent videos (up to 50 videos)
Semantic topic extraction per video via Gemini (theme, named entities, tags)
Keyword frequency analysis across all transcripts (fallback when Gemini is unavailable)
Related MCP server: MCP YouTube Intelligence
You need API keys for three services:
Variable | Where to get it |
| Google Cloud Console → YouTube Data API v3 |
| Apify Console → Account → Integrations → API token |
| Google AI Studio → Get API key |
GEMINI_API_KEY is optional — if omitted, the tool falls back to word-frequency topic extraction instead of semantic analysis. The same fallback applies when a configured Gemini call fails (invalid key, exhausted quota, blocked content); the result's note says why.
Optional
Variable | Default | Description |
|
| Directory where per-channel JSON analysis artifacts are written |
npm install -g mcp-youtube-intelligencemcp-youtube-intelligence --version # or -v — print the installed version and exit
mcp-youtube-intelligence --help # or -h — print usage and exitRunning the command with no flags starts the MCP server itself (stdio transport) — this is what an MCP client config invokes; it's not meant to be run bare in a terminal for interactive use.
Add to your Claude Desktop / MCP client config:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Linux: ~/.config/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"youtube-intelligence": {
"command": "mcp-youtube-intelligence",
"env": {
"YOUTUBE_API_KEY": "your-youtube-api-key",
"APIFY_TOKEN": "your-apify-token",
"GEMINI_API_KEY": "your-gemini-api-key"
}
}
}
}analyze_channel — Extract intelligence from a YouTube channel
channel_url: YouTube channel URL or @handle. Accepts:
- @handle (e.g. @fireship)
- full URL with handle (e.g. youtube.com/@fireship)
- /channel/UC... URL
- bare 24-character UC... channel ID
- legacy /c/name or /user/name URL
max_videos: Number of recent videos to analyze (default: 5, max: 50)Returns a JSON object:
Field | Meaning |
| The resolved channel |
| Your |
| The most recent uploads that were analyzed |
| How many videos were fetched from the channel's uploads playlist |
| How many of those came back with caption content |
| Up to 20 top keywords by frequency across all transcripts. Always computed |
| Per video: |
| Which analysis mode ran. When Gemini was configured but failed, it also says why |
| Where the JSON artifact was written. Absent if the write failed |
Example prompt: "Analyze the @fireship YouTube channel and tell me what topics they cover most."
npm install
npm run build
npm testMIT
Analyze a YouTube channel and return a JSON object with: channel_id, channel_title, channel_url, sample_video_ids[], videos_analyzed (count of videos fetched from playlist), transcripts_available (count with actual caption content), topics[] (top keyword frequencies across all transcripts), topics_structured[] (per-video semantic analysis — each entry has video_id/theme/entities[]/tags[]), note (which analysis mode ran), and optional output_path (local artifact path). Requires YOUTUBE_API_KEY and APIFY_TOKEN; set GEMINI_API_KEY for topics_structured semantic analysis (falls back to keyword-only when absent). Supported channel inputs: @handle (e.g. @fireship), youtube.com/@handle URL, /channel/UC... URL, bare 24-char UCxxxxxx ID, or legacy /c/ and /user/ URLs.
Inputs: channel_url (required), max_videos.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 1 tool
Only one tool exists, so there is no possibility of confusion with other tools.
The single tool name 'analyze_channel' follows a clear verb_noun pattern, making it predictable and unambiguous.
With only one tool for a domain like YouTube intelligence, the surface is too narrow; typical well-scoped servers have 3-15 tools.
The server only offers channel analysis, missing obvious operations like video search, video details, playlist management, and subscription handling, leaving significant gaps.
YouTube transcripts, search, channel browsing, and playlists for AI agents via MCP.
Real-time YouTube transcripts, comments, channels & video search MCP. Local npx or hosted OAuth.
An MCP server that gives any LLM or agent clean YouTube transcripts on demand: a single video, a whole channel, or a playlist, plus AI cleanup of auto-generated captions. API-key auth, credit-based, same backend as the public v1 API. Get a free API key with 25 free credits at youtubetranscriptdownload.com/account.
Real-time video transcripts, RAG captions, metadata, search & comments MCP. OAuth or API key.