Weibo MCP Server
About
基于 Model Context Protocol 的微博数据接口服务器 - 实时获取微博用户信息、动态内容、热搜榜单、粉丝关注数据。支持用户搜索、内容搜索、话题分析,为 AI 应用提供完整的微博数据接入方案。
Details
- Author
- qinyuanpei
- GitHub stars
- 50
- Downloads
- 394
- Categories
- Other
Jump to
- Automatic cookie retrieval – no manual configuration required
- Fetch user profiles, posts, and hot feeds
- Search Weibo users, content, and topics
- Retrieve trending topics and post comments
- Get follower and following lists for a user
- Supports stdio and HTTP (SSE) transport modes
- Includes a standalone CLI for quick data access
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
Weibo MCP ServerCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Install via the uvx package manager, Docker, or from source. Run in either stdio mode (for MCP clients) or HTTP mode (with SSE endpoint). Configure your MCP client with the appropriate command or URL. An optional CLI tool (weibo-cli) is also provided for direct data access without an MCP client.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"weibo mcp server": {
"mcp-server-weibo": {
"command": "docker",
"args": [
"build",
"-t",
"mcp-server-weibo",
"."
]
}
}
}
}
McpServers
{
"mcp-server-weibo": {
"command": "docker",
"args": [
"build",
"-t",
"mcp-server-weibo",
"."
]
}
}
Weibo MCP Server 🚀
基于 Model Context Protocol 的微博数据 API 服务器 - 实时获取微博用户资料、帖子、热搜话题、粉丝/关注数据。支持用户搜索、内容分析和话题发现,适用于 AI 应用。
安装
自动 Cookie 获取: 无需手动配置 Cookie,程序会自动通过微博访客通行证生成有效的访问凭证。
方式一:从包管理器安装(推荐)
```bash
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.



