
YouTube Data API MCP Server
A FastAPI server that enables interaction with YouTube's data through search, video details, channel information, and comment retrieval endpoints.
README
YouTube Data API v3 MCP Server
This is a FastAPI-based server designed to interact with the YouTube Data API v3. It provides endpoints to search for YouTube videos, retrieve video details, get channel information, and fetch video comments.
Features
- Search YouTube videos by query, order, and channel.
- Get detailed information for a specific YouTube video.
- Get detailed information for a YouTube channel by ID or username.
- Retrieve comments for a specific YouTube video.
Requirements
- Python 3.9+
- A Google Cloud Project with the YouTube Data API v3 enabled.
- An API Key for the YouTube Data API v3.
Setup and Installation
-
Clone the repository:
git clone <repository_url> cd youtube-mcp-server
-
Create a virtual environment (recommended):
python -m venv venv source venv/bin/activate # On Windows: .\venv\Scripts\activate
-
Install dependencies:
pip install -r requirements.txt
-
Configure Environment Variables: Create a
.env
file in the root directory of the project based on.env.example
:YOUTUBE_API_KEY=your_youtube_api_key_here
Replace
your_youtube_api_key_here
with your actual YouTube Data API v3 Key. Keep this key secure and do not commit it to version control.
Running the Server
Locally
To run the server locally using Uvicorn:
uvicorn main:app --host 0.0.0.0 --port 8000 --reload
The --reload
flag is useful for development as it restarts the server on code changes.
The API will be accessible at http://localhost:8000
.
Access the interactive API documentation (Swagger UI) at http://localhost:8000/docs
.
Using Docker
-
Build the Docker image:
docker build -t youtube-mcp-server .
-
Run the Docker container: Make sure to pass your API key as an environment variable.
docker run -d -p 8000:8000 --name youtube-server -e YOUTUBE_API_KEY="your_youtube_api_key_here" youtube-mcp-server
Replace
"your_youtube_api_key_here"
with your actual API key.
API Endpoints
All endpoints are prefixed with /youtube/
.
1. Health Check
- GET
/health
- Description: Checks if the server is running.
2. Search YouTube Videos
- GET
/youtube/videos/search
- Description: Searches YouTube videos based on a query.
- Query Parameters:
query
(string, required): The search query string.max_results
(integer, optional, default: 10, max: 50): Maximum number of results.order
(string, optional, default: "relevance"): Order of results (e.g., "date", "viewCount").channel_id
(string, optional): Restricts search to a specific channel.
- Example:
/youtube/videos/search?query=FastAPI%20tutorial&max_results=5
3. Get YouTube Video Details
- GET
/youtube/videos/{video_id}
- Description: Retrieves detailed information for a specific YouTube video.
- Path Parameters:
video_id
(string, required): The ID of the YouTube video.
- Example:
/youtube/videos/dQw4w9WgXcQ
4. Get YouTube Channel Details
- GET
/youtube/channels
- Description: Retrieves detailed information for a YouTube channel by ID or username.
- Query Parameters:
channel_id
(string, optional): The ID of the YouTube channel.username
(string, optional): The username of the YouTube channel (legacy).- Note: At least one of
channel_id
orusername
must be provided.
- Example:
/youtube/channels?channel_id=UC_x5XG1OV2P6wRIMAn-Ny3A
(Google Developers channel) - Example:
/youtube/channels?username=PewDiePie
(Note: Username lookup is less reliable now)
5. Get YouTube Video Comments
- GET
/youtube/videos/{video_id}/comments
- Description: Retrieves comments for a specified YouTube video.
- Path Parameters:
video_id
(string, required): The ID of the YouTube video.
- Query Parameters:
max_results
(integer, optional, default: 100, max: 100): Maximum number of comments to return.
- Example:
/youtube/videos/dQw4w9WgXcQ/comments
Error Handling
The API returns standard HTTP status codes for errors (e.g., 400 Bad Request, 404 Not Found, 500 Internal Server Error) with a JSON payload containing a detail
message.
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。