youtube-research
Enables YouTube integration with Claude Code, including video search, metadata retrieval, transcript fetching, channel exploration, and trending videos.
README
YouTube Research MCP Server
An MCP server for YouTube integration with Claude Code — search videos, get metadata, fetch transcripts, explore channels, and more.
Tools
| Tool | Description | API Quota |
|---|---|---|
youtube_search(query, max_results) |
Search videos by query | 100 + 1 |
youtube_video_info(video_url_or_id) |
Get video metadata by URL or ID | 1 |
youtube_transcript(video_url_or_id, lang) |
Fetch video subtitles with timestamps | 0 (no API) |
youtube_channel_info(channel_url_or_id) |
Get channel stats (subscribers, views, etc.) | 1 |
youtube_channel_videos(channel_url_or_id, max_results) |
List recent videos from a channel | 2 |
youtube_playlist(playlist_url_or_id, max_results) |
List videos in a playlist | 2 |
youtube_comments(video_url_or_id, max_results) |
Get top comments for a video | 1 |
youtube_trending(region_code, max_results) |
Get trending videos by country | 1 |
YouTube Data API v3 free quota: 10,000 units/day.
youtube_searchis the most expensive at ~101 units per call.
Setup
1. Get a YouTube API Key
- Go to Google Cloud Console
- Create a project (or select an existing one)
- Navigate to APIs & Services → Library
- Find and enable YouTube Data API v3
- Go to APIs & Services → Credentials
- Click Create Credentials → API Key
- Copy the key
2. Install Dependencies
cd /path/to/youtube_research
uv sync
3. Configure Claude Code
Copy the example config and add your API key:
cp .mcp.json.example ~/.claude/.mcp.json
Edit ~/.claude/.mcp.json — replace /path/to/youtube_research and YOUR_API_KEY_HERE with actual values.
Important:
.mcp.jsoncontains your API key — do not commit it to git.
Alternatively, place .mcp.json in the project root — the server will only be available when working from that directory.
4. Restart
Restart Claude Code — all 8 tools will become available.
Remote Access (SSE)
To use with Claude.ai web chat or other remote MCP clients, run the server in SSE mode on a VPS:
YOUTUBE_API_KEY=your_key uv run server.py --sse --host 0.0.0.0 --port 8000
Options:
--sse— enable SSE transport (default is stdio)--host— bind address (default:127.0.0.1— use0.0.0.0to expose externally)--port— port number (default:8000)
The server will be available at http://your-vps:8000/sse.
Security: The SSE endpoint has no built-in authentication. For public deployment, use a reverse proxy (nginx) with token-based auth in front of it.
Usage Examples
In Claude Code:
- "Find videos about Python asyncio" →
youtube_search - "Show info for https://youtu.be/dQw4w9WgXcQ" →
youtube_video_info - "Get subtitles for this video" →
youtube_transcript - "How many subscribers does @lexfridman have?" →
youtube_channel_info - "Show latest videos from @ThePrimeagen" →
youtube_channel_videos - "List videos in this playlist: https://youtube.com/playlist?list=..." →
youtube_playlist - "What are people saying about this video?" →
youtube_comments - "What's trending in Japan?" →
youtube_trending
License
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。