server-google-news
【Star-crossed coders unite!⭐️】Model Context Protocol (MCP) server implementation providing Google News search capabilities via SerpAPI, with automatic news categorization and multi-language support.
claude mcp add --transport stdio chanmeng666-server-google-news node dist/index.js \ --env SERP_API_KEY="your-serpapi-key"
How to use
This MCP server provides Google News search capabilities powered by SerpAPI. It exposes a Google News search tool that lets you query news articles, filter by region and language, and refine results by topics or publishers. Typical usage involves sending a request to the server with a tool named google_news_search and a set of parameters such as the query, geographic region, and language. The server automatically categorizes results into topics and supports multiple result types (headlines, stories, related topics, and menu links). If your input language isn’t supported, the server will automatically fall back to English and notify the user as needed. The API surface is designed for AI agents and MCP clients to retrieve structured news data efficiently across languages and locales.
How to install
Prerequisites:
- Node.js (LTS) and npm installed on your system
- Access to install npm packages from the registry
Step-by-step installation:
- Install dependencies (clone the repo if you have it locally, or install the npm package):
# If you have the repository locally
git clone https://github.com/ChanMeng666/server-google-news.git
cd server-google-news
npm install
- Build the server (if a build step is required by the project):
npm run build
- Set up environment variables:
- Obtain a SerpAPI key from serpapi.com
- Create a config file or set environment variables; for example:
export SERP_API_KEY=your-serpapi-key
- Run the server:
npm start
Notes:
- If you are using Windows or a different environment, adapt the path to the built server entry point (for example, dist/index.js).
- The server expects a SerpAPI key for authenticating requests to Google News results.
Additional notes
Tips and common considerations:
- Set SERP_API_KEY to a valid SerpAPI key. Without it, searches will fail.
- The API supports language and region codes (hl and gl). Use standard codes like hl='en' and gl='us'. If a code isn’t supported, the server will fall back to English.
- You can pass additional tokens (topic_token, publication_token, story_token, section_token) to refine results to specific topics, publishers, or story coverage.
- If you encounter rate limits, review your SerpAPI plan and adjust query frequency or implement caching at the MCP client level.
- Ensure your environment has network access to SerpAPI endpoints and that any firewall rules permit outbound HTTPS traffic.
Related MCP Servers
mcp-gemini
This project provides a dedicated MCP (Model Context Protocol) server that wraps the @google/genai SDK. It exposes Google's Gemini model capabilities as standard MCP tools, allowing other LLMs (like Cline) or MCP-compatible systems to leverage Gemini's features as a backend workhorse.
mcp-claude-spotify
An integration that allows Claude Desktop to interact with Spotify using the Model Context Protocol (MCP).
architect
A powerful, self-extending MCP server for dynamic AI tool orchestration. Features sandboxed JS execution, capability-based security, automated rate limiting, marketplace integration, and a built-in monitoring dashboard. Built for the Model Context Protocol (MCP).
unity
A Unity MCP server that allows MCP clients like Claude Desktop or Cursor to perform Unity Editor actions.
ObsidianMCPServer
A Model Context Protocol (MCP) server that enables AI assistants to interact with your Obsidian vault
skylight
MCP server for Skylight family calendar - enables AI assistants to manage calendars, chores, lists, meals, and rewards