sogou-weixin

This MCP server exposes a tool for searching WeChat official account articles through the Sogou WeChat platform. It is packaged as an MCP service so other AI agents or systems can call the tool using the MCP protocol. The server runs as a Python application and is intended to be managed with uv, a dependency and process manager. After starting the server, clients can send MCP requests that invoke the search_wechat_articles tool and receive structured article results including title, snippet, URL, source, and date. The tool is designed to support keyword queries and a configurable number of results (top_num).

Prerequisites:

• Python 3.10 or higher
• uv installed (dependency manager for Python projects)

Installation steps:

1. Install uv if not already installed: curl -LsSf https://astral.sh/uv/install.sh | sh

2. Clone or download the repository and navigate to the project directory: git clone https://github.com/your-org/sogou-weixin-mcp-server.git cd sogou-weixin-mcp-server

3. Install dependencies using uv: uv sync

4. Run the MCP server: uv run server.py

5. The server will start and listen for MCP client requests. Ensure network access to Sogou WeChat services if applicable.

Tips and considerations:

• Ensure Python 3.10+ is in use, as the server relies on modern Python features.
• The server exposes a tool named search_wechat_articles. Use the MCP tooling interface to specify input with fields such as query (string) and top_num (integer, default 18).
• If you encounter network or rate-limiting issues from the Sogou WeChat service, adjust query frequency or implement caching.
• The output includes structured article data (title, snippet, URL, source, date) to facilitate downstream processing.
• If running behind a proxy or in a restricted environment, set appropriate HTTP_PROXY/HTTPS_PROXY environment variables.
• For debugging, increase UV log level or check server.py for any additional runtime options.