Skip to main content
Glama
mcp-server-weibo

mcp-server-weibo

mcp-server-weibo

微博 MCP 服务器,通过 Model Context Protocol 为 AI 助手提供微博数据查询能力。

功能

工具

说明

search_users

根据关键词搜索微博用户

get_profile

获取用户资料

get_feeds

获取用户动态

get_hot_feeds

获取用户热门动态

get_trendings

获取微博热搜榜

search_content

搜索微博内容

search_topics

搜索微博话题

get_followers

获取用户关注列表

get_fans

获取用户粉丝列表

get_comments

获取帖子评论

Related MCP server: TwitterAPI.io MCP Server

安装

在 MCP 客户端的配置中添加:

从 GitHub 源码安装:

{
  "mcpServers": {
    "weibo": {
      "command": "uvx",
      "args": [
        "--from",
        "git+https://github.com/InfernalAzazel/mcp-server-weibo.git",
        "mcp-server-weibo"
      ],
      "env": {
        "COOKIE": "你的微博 cookie"
      },
    }
  }
}

本地开发:

uv pip install -e .
# 或
pip install -e .

配置

需要配置微博 Cookie 才能调用 API。在 env 中设置 COOKIE,或在项目目录下创建 .env:

COOKIE=你的微博Cookie字符串

或通过命令行保存到 .env:

mcp-server-weibo --cookie "你的微博Cookie"

获取 Cookie:登录 m.weibo.cn,在浏览器开发者工具中复制请求头里的 Cookie。

使用

stdio(默认)

mcp-server-weibo
# 或
mcp-server-weibo stdio

HTTP 模式

mcp-server-weibo http
# 默认端口 4200,可通过环境变量 PORT 修改
PORT=8080 mcp-server-weibo http

开发调试

uv run fastmcp dev inspector src/mcp_server_weibo/server.py --ui-port 3666 --server-port 3667

测试

# 运行所有测试
uv run pytest tests/ -v

# 需要 COOKIE 的 API 测试(未配置会跳过)
uv run pytest tests/test_weibo.py -v

Available Tools

10 tools
get_commentsB

获取指定微博帖子的评论。

返回: list[dict]: 包含评论信息的字典列表

Inputs: feed_id (required), page. Returns: result

get_fansC

获取微博用户粉丝列表。

返回: list[dict]: 包含粉丝信息的字典列表

Inputs: uid (required), limit, page. Returns: result

get_feedsC

获取微博用户动态。

返回: list[dict]: 包含动态信息的字典列表

Inputs: uid (required), limit. Returns: result

get_followersA

获取微博用户关注列表。

返回: list[dict]: 包含关注信息的字典列表

Inputs: uid (required), limit, page. Returns: result

get_hot_feedsC

获取微博用户热门动态。

返回: list[dict]: 包含热门动态信息的字典列表

Inputs: uid (required), limit. Returns: result

get_profileB

获取微博用户资料信息。

返回: dict: 包含用户资料信息的字典

Inputs: uid (required). Returns: object

get_trendingsB

获取当前微博热搜话题。

返回: list[dict]: 包含热搜条目的字典列表

Inputs: limit. Returns: result

search_contentB

根据关键词搜索微博内容。

返回: list[dict]: 包含搜索结果的字典列表

Inputs: keyword (required), limit, page. Returns: result

search_topicsC

根据关键词搜索微博话题。

返回: list[dict]: 包含搜索结果的字典列表

Inputs: keyword (required), limit, page. Returns: result

search_usersA

根据关键词搜索微博用户。

返回: list[dict]: 包含用户信息的字典列表

Inputs: keyword (required), limit, page. Returns: result

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.6/5.0

    Scored across 10 tools

    Disambiguation5/5

    Each tool targets a distinct aspect of Weibo data: comments, fans, feeds, followers, hot feeds, profile, trending, and searches for content, topics, and users. No two tools have overlapping purposes.

    Naming Consistency5/5

    All tools follow a consistent verb_noun pattern using snake_case: get_* for retrieval and search_* for searching. This makes the set predictable and easy to navigate.

    Tool Count5/5

    10 tools cover the essential read operations for a Weibo server without being excessive. Each tool earns its place, providing a well-scoped interface.

    Completeness4/5

    The set covers core read operations: user profile, feeds, comments, followers/fans, trending, and search across multiple dimensions. Missing might be a direct 'get_post' endpoint, but feeds and search suffice. Limited to read-only, which is acceptable for the stated domain.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • F
      license
      Not graded
      quality
      D
      maintenance
      Enables AI assistants to crawl and extract data from Chinese social media platforms like Bilibili, Xiaohongshu, and Douyin. Provides search, content detail retrieval, and creator information tools with persistent browser sessions and QR code login support.
      80
      -
    • A
      license
      Not graded
      quality
      D
      maintenance
      Provides AI agents and coding assistants with Twitter data access including tweets, user profiles, followers, and search functionality.
      MIT
    • A
      license
      A
      quality
      D
      maintenance
      Enables AI assistants to search real content from Xiaohongshu and Zhihu, supporting keyword search, note details, and question retrieval.
      8
      4
      MIT