Weibo

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。
  • python

30

GitHub Stars

python

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

This MCP Server provides real-time access to Weibo data including user profiles, feeds, trends, and social connections. It enables you to plug Weibo data into AI apps, build search features, topic analysis, and engagement metrics with a ready-to-use MCP endpoint.

How to use

You connect to this Weibo MCP Server through your MCP client by registering one or more MCP endpoints. The HTTP endpoint gives you a remote MCP server URL, while the stdio endpoint lets you run the server locally using the provided command and arguments. In practice, you will configure your MCP client with either the http URL or the stdio command so your applications can query user profiles, feeds, topics, comments, followers, and other data in real time.

How to install

Prerequisites: ensure you have a supported runtime for your MCP client. The server examples rely on the MCP runner tooling to launch a server as a process or via an HTTP URL.

Option A: Install from source (stdio runtime) Use this to run the Weibo MCP Server as a local process through the MCP runner. This approach uses the stdio configuration to start the server.

{
  "mcpServers": {
    "weibo": {
      "command": "uvx",
      "args": [
        "--from",
        "git+https://github.com/qinyuanpei/mcp-server-weibo.git",
        "mcp-server-weibo"
      ]
    }
  }
}

Option B: Install from package manager (stdio runtime) Use this to run the Weibo MCP Server as a local process via a package manager flow.

{
  "mcpServers": {
    "weibo": {
      "command": "uvx",
      "args": ["mcp-server-weibo"]
    }
  }
}

Option C: Run via Docker (http runtime) If you prefer containerized deployment, build and run the server in a Docker container. This exposes the MCP endpoint on port 4200 by default.

docker build -t mcp-server-weibo .
docker run -d --name mcp-server-weibo -p 4200:4200 mcp-server-weibo

HTTP endpoint configuration example

{
  "mcpServers": {
    "weibo": {
      "url": "http://localhost:4200/mcp",
      "args": []
    }
  }
}

Available tools

search_users

Search Weibo users by keyword and limit, returning user profiles with id, screen_name, profile images, follower counts, and verification status.

get_profile

Fetch detailed information for a single user by their UID, including profile metadata and verification status.

get_feeds

Retrieve a user’s recent posts/feeds with metadata like text, creation time, source, and engagement counts.

get_trendings

Obtain current hot topics on Weibo with description and a link to the search page.

search_content

Search Weibo content by keyword and page, returning posts with user metadata and engagement metrics.

search_topics

Query Weibo topics by keyword and limit, returning topic titles, descriptions, and URLs.

get_comments

Get comments for a specific feed id, including comment text, author, and reply references.

get_hot_feeds

Fetch popular posts with engagement metrics and author information.

get_followers

List users followed by a given uid, including profile information and follow counts.

get_fans

List fans/followers of a given uid, including profile information and follow counts.

Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational