mcp_newsnow

[](https://mseep.ai/app/sligter-mcp-newsnow) # MCP NewNow Server [](https://github.com/anthropics/anthropic-tools) A news aggregation server based on Model Context Protocol (MCP), providing trending news and topics from multiple platforms through the [Newsnow](https://github.com/ourongxing/newsnow) API. ## Features - **Multi-platform Hotspot Aggregation**: One-stop access to trending content from over 14 platforms including Coolapk, Zhihu, Weibo, Bilibili, Douyin, GitHub, etc. - **Chinese and English Source Name Recognition**: Supports news source names in both Chinese and English, with fuzzy matching capabilities. - **Custom API Endpoint**: Configure the NewNow API endpoint via environment variables or command-line arguments. ## Installation ### Method 1: Install from PyPI ```bash # Install using pip pip install mcp-newsnow # Or install using uv uv pip install mcp-newsnow ``` ### Method 2: Configure Claude Desktop Add the server configuration to the Claude Desktop configuration file: **macOS**: `~/Library/Application Support/Claude/claude_desktop_config.json` **Windows**: `%APPDATA%\Claude\claude_desktop_config.json` Add the following configuration: ```json { "mcpServers": { "get_news": { "command": "uvx", "args": [ "mcp-newsnow" ] } } } ``` ## Usage ### Using Claude Desktop 1. Install and configure Claude Desktop. 2. Add the above MCP server configuration to the configuration file. 3. Restart Claude Desktop. 4. Use news-related tools in the conversation. ### Using MCP CLI for Development ```bash # Set the API endpoint via environment variable NEWS_API_URL=https://newsnow.example.com # Run tests mcp test server.py ``` ## Available Tools ### 1. Get Single Source News (get_newsnow) ```python async def get_newsnow(source: str) -> dict[str, Any] | None ``` Fetch the latest news from the specified source. **Parameters**: - `source`: News source name (supports both Chinese and English, e.g., "知乎", "zhihu", "B站", etc.) **Returns**: A dictionary containing news data. ### 2. Get Multi-source News (get_multi_news) ```python async def get_multi_news(sources: list[str] = None) -> dict[str, Any] ``` Fetch the latest news from multiple sources (up to 5). **Parameters**: - `sources`: List of news source names. **Returns**: A dictionary containing data from multiple news sources. ### 3. Get All Source News (get_all_news) ```python async def get_all_news() -> dict[str, Any] ``` Fetch data from all configured news sources. **Returns**: A dictionary containing all news source data and metadata. ### 4. List Available News Sources (list_sources) ```python async def list_sources() -> dict[str, str] ``` List all available news sources and their Chinese names. **Returns**: A dictionary mapping news source IDs to Chinese names. ## Environment Variables - `NEWS_API_URL`: Base URL for the Newsnow API (default: "https://newsnow.busiyi.world/") ## Supported News Sources - 酷安 (coolapk) - B站热搜 (bilibili-hot-search) - 知乎 (zhihu) - 微博 (weibo) - 今日头条 (toutiao) - 抖音 (douyin) - GitHub趋势 (github-trending-today) - Linux热榜 (linuxdo-hot) - 贴吧 (tieba) - 华尔街见闻 (wallstreetcn) - 澎湃新闻 (thepaper) - 财联社 (cls-hot) - 雪球 (xueqiu) - 快手 (kuaishou) ## Contribution Guidelines Contributions are welcome! Here are some potential areas for improvement: - Add support for more news sources. - Enhance content extraction and processing capabilities. - Add a caching layer to reduce API calls. - Improve error handling and retry mechanisms. - Add result filtering and classification features. ## License This project is licensed under the MIT License.