MediaCrawler MCP Server
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@MediaCrawler MCP ServerCrawl Bilibili for keyword 'AI' and store in MySQL."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
🔥 MediaCrawler_MCP_Server - MCP for MediaCrawler 🕷️
🔗 MediaCrawler仓库地址
https://github.com/NanmiCoder/MediaCrawler
🔧 基于MediaCrawler改进
python版本:所有包版本可用于python 3.13,以支持mcp的使用
mysql存储:如表已经存在,初始化不会覆盖原有数据
✨ 更多设置(config)可见MediaCrawler仓库
🧰 可使用的MCP工具
crawl_search(platform: str, store_type: str, keywords: str) - Start the crawler for the media platform by keywords
crawl_detail(platform: str, store_type: str, video_id: list): - Start the crawler for the media platform by video ID
crawl_creator(platform: str, store_type: str, creator_id: list) - Start the crawler for the media platform by creator id.
📦 Python包安装
# 进入项目目录
cd MediaCrawler_MCP_Server
# 使用 uv sync 命令来保证 python 版本和相关依赖包的一致性
uv sync🌐 浏览器驱动安装
# 安装浏览器驱动
uv run playwright install⚙️ 设置
设置环境变量:
MYSQL_DB_HOST=localhost # Database host
MYSQL_DB_PORT=3306 # Optional: Database port (defaults to 3306 if not specified)
MYSQL_DB_USER=your_username
MYSQL_DB_PWD=your_password
MYSQL_DB_NAME=your_database
CRAWLER_MAX_NOTES_COUNT=20 # number of notes you want to crawl
MAX_CONCURRENCY_NUM=1 # number of concurrent crawlers
ENABLE_GET_COMMENTS=true # crawl the comments or not🚀 使用
添加至 claude_desktop_config.json or cline_mcp_settings.json
"mediacrawler": {
"disabled": false,
"timeout": 600,
"type": "stdio",
"command": "uv",
"args": [
"--directory",
"path/to/MediaCrawler_MCP_Server",
"run",
"main.py"
],
"env": {
"MYSQL_DB_HOST": "localhost",
"MYSQL_DB_PORT": "3306",
"MYSQL_DB_USER": "your_username",
"MYSQL_DB_NAME": "your_database",
"MYSQL_DB_PWD": "your_password",
"CRAWLER_MAX_NOTES_COUNT": "20",
"MAX_CONCURRENCY_NUM": "1",
"ENABLE_GET_COMMENTS": "true"
}
}🌰 例子
帮我爬取b站视频资料,关键词为"钱",存储模式为mysql。帮我爬取b站视频号为BV1d54y1g7db,BV1Sz4y1U77N的视频存储模式为json。帮我爬取b站up主视频资料,其id为20813884,存储模式为csv。
This server cannot be installed
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/Bowenwin/MediaCrawler_MCP_Server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server