Google News MCP Server
About
Integrates with Google News via SerpAPI to enable querying and retrieving current news articles, headlines, and related information for applications like news aggregation and trend analysis.
Details
- Author
- ChanMeng666
- Repository
- ChanMeng666/server-google-news
- GitHub stars
- 41
- Downloads
- 749
- License
- MIT License
- Categories
- Search, Community, Other, Productivity, Developer Tools, Design, AI, Media, Infrastructure, API, Frontend
- Tags
Jump to
This server includes comprehensive monitoring and optimization for AI agent usage.
- Citation Success Rate: Percentage of successful tool calls
- AI Traffic Conversion Rate: Percentage of AI agents successfully using the tool
- Query Coverage Rate: Percentage of queries returning relevant results
- Response Time: Average response time for tool calls
- Categorization Accuracy: Accuracy of automatic news categorization
- Link Carry Rate: Percentage of responses including source links
interface GEOMonitoringConfig { trackingEnabled: boolean; metricsEndpoint: string; reportingInterval: number; // minutes alertThresholds: { errorRate: number; responseTime: number; successRate: number; satisfactionScore: number; }; }
- Real-time metrics collection
- Automated alerting for performance issues
- Query pattern analysis for optimization
- Agent usage tracking and analytics
- Continuous monitoring of AI agent satisfaction
- Query success rate analysis
- Response time optimization
- Categorization accuracy improvements
For technical implementation details, see](https://smithery.ai/server/@chanmeng666/google-news-server)src/geo-metrics.ts.
This server provides comprehensive structured data for AI agents and search engines.
The server includes structured data following Schema.org standards:
- Software application metadata
- Feature descriptions and capabilities
- Technical requirements and dependencies
- Usage patterns and integration guidelines
- Protocol Version: 1.0.0
- Tool Name:google_news_search
- Response Format: Structured text with categorized results
- Rate Limits: 2 requests/second, 5 concurrent requests
- llms.txt: Comprehensive AI usage guide at root level
- Structured Metadata: Enhanced manifest.json with AI-specific information
- Error Handling: AI-friendly error messages and fallbacks
- Documentation: Detailed usage examples and best practices
- Designed for seamless integration with other MCP servers
- Optimized for AI agent workflows
- Supports various AI platforms and frameworks
- Provides clear error handling and debugging information
For complete structured data, seestructured-data.json.
A hosted deployment is available onFronteir AI.
Chan Meng
Need a custom app like this one? I build them — let's talk.
Search global news using natural language. Webz.io News Search API returns the most relevant articles and content, with filters for source, country, language, date, sentiment, and category.
Search for IP addresses using Chaitin's IP Intelligence API.
Get any answer from the Facebook Ads Library, conduct deep research including messaging, creative testing and comparisons in seconds.
A Model Context Protocol (MCP) server providing access to Google Programmable Search Engine (PSE) and Custom Search Engine (CSE).
A Model Context Protocol (MCP) server providing access to Google Search Console.
A Model Context Protocol (MCP) server for the Open Library API that enables AI assistants to search for book and author information.
An enhanced MCP server for SearXNG web searching, utilizing a category-aware web-search, web-scraping, and includes a date/time retrieval tool.
Local RAG (on-premises) with MCP server.
Setting up with Highlight
Follow these steps to add this server as a custom Highlight plugin:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
Google News MCP ServerCommand (node, npx, python, etc.)nodeArguments-
Argument 1
D:\github_repository\path_to\dist\index.js
Environment-
SERP_API_KEY
your-api-key
Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
-
Argument 1
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Install via npm, Smithery, or mcp-get. Configure your SerpAPI key in claude_desktop_config.json, then build and start the server. The exposed tool is google_news_search with parameters for query, country, language, and various tokens.
google_news_search
Search for news articles based on a query. Parameters: q (string) for the search query, gl (string) for the country code, hl (string) for the language code, topic_token (string) for specific news topics, publication_token (string) for specific publishers, story_token (string) for full coverage of a story, section_token (string) for specific sections.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"google news mcp server": {
"env": {
"SERP_API_KEY": "your-api-key"
},
"args": [
"D:\\github_repository\\path_to\\dist\\index.js"
],
"command": "node"
}
}
}
Linux
{
"env": {
"SERP_API_KEY": "your-api-key"
},
"args": [
"D:\\github_repository\\path_to\\dist\\index.js"
],
"command": "node"
}
Macos
{
"env": {
"SERP_API_KEY": "your-api-key"
},
"args": [
"D:\\github_repository\\path_to\\dist\\index.js"
],
"command": "node"
}
Windows
{
"env": {
"SERP_API_KEY": "your-api-key"
},
"args": [
"/c",
"D:\\Program\\nvm\\node.exe",
"D:\\github_repository\\path_to\\dist\\index.js"
],
"command": "cmd"
}
A Model Context Protocol (MCP) server implementation that provides Google News search capabilities via SerpAPI integration. Automatically categorizes news results and supports multiple languages and regions.
https://github.com/user-attachments/assets/1cc71c27-f840-4c94-9ab5-460d84ba4779
Comprehensive search capabilities including query-based search, topic search, publication filtering and story coverage.
Supports multiple languages and regions through configurable language and country codes.
Automatically categorizes news results into topics like AI & Technology, Business, Science & Research, and Healthcare.
Handles various news result types including headlines, stories, related topics and menu links.
Comprehensive error handling for API failures and invalid inputs, with helpful error messages.
Automatic fallback to English for unsupported language codes with appropriate user notifications.
Before getting started, you'll need to obtain a SerpApi key. Here's how:
-
VisitSerpApi websiteand create an account
After registration, go to your Dashboard:
- Locate the "API Key" section
- Copy your API key
- New users get 250 free API calls
- Free tier: 250 searches per month
- Paid plans start at $75/month for 5000 searches
- Billing based on successful API calls
- Multiple payment methods: Credit Card, PayPal, etc.
- Request Rate: 2 requests/second
- IP Restrictions: None
- Concurrent Requests: 5
- Response Cache Time: 1 hour
👩🔧 Solution for MCP Servers Connection Issues with NVM/NPM
Click to view my configuration solution 👉https://github.com/modelcontextprotocol/servers/issues/76
- Configure environment: Modify yourclaude_desktop_config.jsonwith the following content (adjust paths according to your system):
"google-news": { "command": "D:\\Program\\nvm\\node.exe", "args": [ "D:\\github_repository\\path_to\\dist\\index.js" ], "env": { "SERP_API_KEY": "your-api-key" } }
- Verify API key configuration inclaude_desktop_config.json
- Confirm API key is active in SERP API dashboard
- Check network connectivity
- Verify API call quota hasn't been exceeded
- Validate request parameter format
The evals package loads an mcp client that then runs the index.ts file, so there is no need to rebuild between tests. You can load environment variables by prefixing the npx command. Full documentation can be foundhere.
OPENAI_API_KEY=your-key npx mcp-eval src/evals/evals.ts src/index.ts
To install Google News for Claude Desktop automatically viaSmithery:
npx -y @smithery/cli install @chanmeng666/google-news-server --client claude
npx @michaellatman/mcp-get@latest install @chanmeng666/google-news-server
If you are using an old version of Windows PowerShell, you may need to runSet-ExecutionPolicy Bypass -Scope Processbefore this command.
# Using npm npm i @chanmeng666/google-news-server # or npm install @chanmeng666/google-news-server # Using yarn yarn add @chanmeng666/google-news-server # Using pnpm pnpm add @chanmeng666/google-news-server
The server implements the Model Context Protocol and exposes a Google News search tool with the following parameters:
- q: Search query string
- gl: Country code (e.g., 'us', 'uk')
- hl: Language code (e.g., 'en', 'es')
- topic_token: Token for specific news topics
- publication_token: Token for specific publishers
- story_token: Token for full coverage of a story
- section_token: Token for specific sections
# Run in development mode with hot reload npm run dev # Run linting npm run lint # Run tests npm run test
This MCP server is optimized for AI agent usage with comprehensive instructions and structured data.
{ "tool": "google_news_search", "parameters": { "q": "artificial intelligence latest developments", "gl": "us", "hl": "en" } }
- Automatic Categorization: News results are automatically sorted into relevant categories
- Structured Output: Returns formatted data optimized for AI processing
- Multi-language Support: Supports various languages with automatic fallbacks
- Error Handling: Comprehensive error messages and graceful degradation
The server returns categorized news with the following structure:
- Categories: AI & Technology, Business, Science & Research, Healthcare, General
- Article Fields: title, source, link, date, snippet, authors
- Metadata: timestamp, menu_links for related topics
- Use specific, descriptive keywords for better results
- Leverage automatic categorization for topic-based workflows
- Implement proper error handling and retry logic
- Respect API rate limits (2 requests/second)
- Parse structured responses for better context understanding
- News Monitoring: Use company names or stock symbols for business news
- Research Exploration: Leverage topic tokens for field-specific searches
- Breaking News: Use "breaking news" or "latest news" queries
- Multi-language: Combine appropriate gl and hl parameters
- Invalid API key: Check SERP_API_KEY environment variable
- Unsupported language: Server auto-falls back to English
- Rate limiting: Respect 2 requests/second limit
- Invalid parameters: Validate parameter types before calling
Generative Engine Optimization (GEO) Features
This server includes comprehensive monitoring and optimization for AI agent usage.
- Citation Success Rate: Percentage of successful tool calls
- AI Traffic Conversion Rate: Percentage of AI agents successfully using the tool
- Query Coverage Rate: Percentage of queries returning relevant results
- Response Time: Average response time for tool calls
- Categorization Accuracy: Accuracy of automatic news categorization
- Link Carry Rate: Percentage of responses including source links
interface GEOMonitoringConfig { trackingEnabled: boolean; metricsEndpoint: string; reportingInterval: number; // minutes alertThresholds: { errorRate: number; responseTime: number; successRate: number; satisfactionScore: number; }; }
- Real-time metrics collection
- Automated alerting for performance issues
- Query pattern analysis for optimization
- Agent usage tracking and analytics
- Continuous monitoring of AI agent satisfaction
- Query success rate analysis
- Response time optimization
- Categorization accuracy improvements
For technical implementation details, seesrc/geo-metrics.ts.
This server provides comprehensive structured data for AI agents and search engines.
The server includes structured data following Schema.org standards:
- Software application metadata
- Feature descriptions and capabilities
- Technical requirements and dependencies
- Usage patterns and integration guidelines
- Protocol Version: 1.0.0
- Tool Name:google_news_search
- Response Format: Structured text with categorized results
- Rate Limits: 2 requests/second, 5 concurrent requests
- llms.txt: Comprehensive AI usage guide at root level
- Structured Metadata: Enhanced manifest.json with AI-specific information
- Error Handling: AI-friendly error messages and fallbacks
- Documentation: Detailed usage examples and best practices
- Designed for seamless integration with other MCP servers
- Optimized for AI agent workflows
- Supports various AI platforms and frameworks
- Provides clear error handling and debugging information
For complete structured data, seestructured-data.json.
A hosted deployment is available onFronteir AI.
Chan Meng
Need a custom app like this one? I build them — let's talk.
Search global news using natural language. Webz.io News Search API returns the most relevant articles and content, with filters for source, country, language, date, sentiment, and category.
Search for IP addresses using Chaitin's IP Intelligence API.
Get any answer from the Facebook Ads Library, conduct deep research including messaging, creative testing and comparisons in seconds.
A Model Context Protocol (MCP) server providing access to Google Programmable Search Engine (PSE) and Custom Search Engine (CSE).
A Model Context Protocol (MCP) server providing access to Google Search Console.
A Model Context Protocol (MCP) server for the Open Library API that enables AI assistants to search for book and author information.
An enhanced MCP server for SearXNG web searching, utilizing a category-aware web-search, web-scraping, and includes a date/time retrieval tool.
Local RAG (on-premises) with MCP server.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.



