sogou-weixin-mcp-server
Enables searching for WeChat official account articles through the Sogou WeChat platform, returning structured article information.
README
Sogou WeChat Search MCP Server
This project provides a tool for searching articles through Sogou WeChat and encapsulates it as an MCP (Model Context Protocol) server.
Key Highlights:
- WeChat Article Search: Enables searching for WeChat official account articles through the Sogou WeChat platform.
- Flexible Query: Supports searching by keywords and specifying the number of articles to return.
- Structured Output: Returns structured article information including title, snippet, URL, source, and date, facilitating further processing.
- MCP Server Integration: Encapsulates the WeChat article search functionality as an MCP tool, allowing other AI agents or systems to call it via the MCP protocol.
How to Use
Quick Start (Recommended)
You can run the server directly with uvx — no clone, no install, no setup:
uvx --from git+https://github.com/ptbsare/sogou-weixin-mcp-server.git sogou-weixin-mcp-server
This downloads and runs the latest version in one shot.
1. Environment Setup (Local Development)
Ensure your system has Python 3.10 or higher installed.
It is recommended to use uv for dependency management:
# Install uv (if not already installed)
curl -LsSf https://astral.sh/uv/install.sh | sh
# Clone the repository
git clone https://github.com/ptbsare/sogou-weixin-mcp-server.git
cd sogou-weixin-mcp-server
# Install dependencies using uv
uv sync
2. Usage as an MCP Server
You can run this project as an MCP server, allowing other AI agents or systems to call the search_wechat_articles tool via the MCP protocol.
# Run via uv (local directory)
uv run sogou-weixin-mcp-server
# Or run the script directly
uv run server.py
Once the server starts, it will listen for MCP client requests over stdio.
3. Claude MCP Server Configuration Example
Below is an example mcp_server.json configuration file to connect this MCP server to Claude:
Option A: Using uvx (no local clone needed)
{
"mcp_servers": [
{
"name": "sogou-wechat-search",
"type": "stdio",
"command": ["uvx", "--from", "git+https://github.com/ptbsare/sogou-weixin-mcp-server.git", "sogou-weixin-mcp-server"]
}
]
}
Option B: Using local directory
{
"mcp_servers": [
{
"name": "sogou-wechat-search",
"type": "stdio",
"command": ["uv", "--directory", "/path/to/sogou-weixin-mcp-server/", "run", "server.py"]
}
]
}
4. Available Tools
search_wechat_articles
Search for WeChat articles via Sogou WeChat.
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
query |
string | Yes | — | Search keyword |
top_num |
integer | No | 18 | Maximum number of articles to return |
Returns: A list of dictionaries, each containing:
title— Article titlesnippet— Article summary/snippeturl— Article URLsource— WeChat official account namedate— Publication date
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。