We're excited to announce the launch of the AllNewsAPI MCP Server – a Model Context Protocol integration that brings real-time news data directly to your AI assistants and development tools.

What is MCP?

The Model Context Protocol (MCP) is an open standard that enables AI assistants to securely connect to external data sources and tools. Think of it as a universal adapter that lets your AI assistant access real-world information beyond its training data.

With MCP, your AI can:

  • Access real-time data from APIs
  • Execute tools and functions
  • Retrieve context-specific information
  • Provide more accurate, up-to-date responses

Why We Built This

Developers using AI assistants like Claude, Cursor, and VS Code Copilot often need access to current news data for:

  • Research and analysis - Understanding current events and trends
  • Content creation - Writing articles with up-to-date information
  • Market intelligence - Tracking industry news and competitor activity
  • Application development - Building news-powered features with AI assistance
  • Data journalism - Analyzing news patterns and sentiment

Previously, you'd need to manually search for news, copy-paste articles, or write custom integrations. Now, your AI assistant can access AllNewsAPI directly through natural language queries.

Key Features

Access news articles with advanced filtering:

  • Date ranges - From the last hour to 10 years of historical data
  • Languages - 22 languages including English, Spanish, Chinese, Arabic, and more
  • Countries - 244 countries worldwide
  • Categories - Technology, business, sports, entertainment, health, science, and more
  • Keywords - Search for specific topics, companies, or events

Real-Time Headlines

Get the latest breaking news and top headlines with customizable parameters. Perfect for staying informed about rapidly developing stories.

LLM-Optimized Responses

Clean, formatted output designed specifically for AI consumption. The server handles all the complexity of API calls, parameter validation, and response formatting.

Robust Error Handling

  • Parameter validation against official supported values
  • Graceful handling of network issues
  • Proper rate limit management

Getting Started

Setting up the AllNewsAPI MCP server takes just a few minutes.

Prerequisites

Installation

Add this configuration to your MCP client settings:

{
  "mcpServers": {
    "allnewsapi": {
      "command": "npx",
      "args": [
        "allnewsapi-mcp@latest",
        "--apikey",
        "YOUR_API_KEY_HERE"
      ]
    }
  }
}

That's it! No installation, no build steps – just add the config and start using it.

Configuration Locations

Claude Desktop:

  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Windows: %APPDATA%\Claude\claude_desktop_config.json

Cursor:

  • Settings → MCP Servers → Add Server

VS Code:

  • .vscode/mcp.json in your workspace

Windsurf:

  • Settings → Extensions → MCP Configuration

Example Usage

Once configured, you can ask your AI assistant natural language questions like:

Technology News:

"Get me the latest technology news from the US"

Climate Coverage:

"Find news articles about climate change from European sources"

Business Headlines:

"Show me top business headlines from the past week"

Cryptocurrency Updates:

"Search for cryptocurrency news in English from the last month"

Sports from Multiple Countries:

"Get sports headlines from Canada and Australia"

The AI assistant will use the MCP server to fetch relevant articles and provide you with formatted, up-to-date information.

Real-World Use Cases

1. Content Research

Before:

You: "I need to write an article about AI regulation"
AI: "Based on my training data from 2023..."

After:

You: "Find recent news about AI regulation in the EU"
AI: *Uses MCP to fetch latest articles*
"Here are the most recent developments in EU AI regulation:
1. New AI Act provisions announced last week...
2. Tech companies respond to compliance requirements...
[with actual current data]"

2. Market Intelligence

Track competitor news, industry trends, and market movements in real-time:

"Monitor news about electric vehicle manufacturers in the past 24 hours"

3. Development Assistance

Build news-powered features with AI help:

"Help me write a function that fetches technology news 
from Asian countries and filters by sentiment"

The AI can now access real data to provide working code examples.

4. Research and Analysis

Analyze news patterns and trends:

"Compare coverage of renewable energy across US, 
European, and Asian news sources this month"

Technical Details

The AllNewsAPI MCP server is built with:

  • TypeScript - Type-safe implementation
  • Model Context Protocol SDK - Official MCP implementation
  • ES Modules - Modern JavaScript with top-level await
  • Comprehensive validation - All parameters validated against official API specs

Available Tools

The server exposes two main tools:

1. search_news

  • Search for news articles with advanced filtering
  • Parameters: query, language, country, category, date ranges, and more
  • Returns: Formatted list of articles with titles, descriptions, URLs, and metadata

2. get_headlines

  • Get top headlines from specific countries or categories
  • Parameters: country, category, language
  • Returns: Latest breaking news and top stories

Supported Parameters

Languages: Arabic, Chinese, Dutch, English, French, German, Greek, Hebrew, Hindi, Italian, Japanese, Korean, Norwegian, Polish, Portuguese, Romanian, Russian, Spanish, Swedish, Turkish, Ukrainian, Vietnamese (22 languages total)

Categories: General, Technology, Business, Sports, Entertainment, Health, Science

Countries: 244 countries including US, UK, Canada, Australia, Germany, France, Japan, India, Brazil, and more

Regions: North America, Europe, Asia, Middle East, Africa, Latin America, Oceania

Security and Privacy

  • API keys are never exposed - Keys are configured locally and never sent to third parties
  • Direct API communication - The MCP server communicates directly with AllNewsAPI
  • No data storage - No caching or storage of your queries or results
  • Rate limit compliance - Respects your API plan limits

Pricing

The MCP server itself is completely free and open source. You only pay for your AllNewsAPI usage:

  • Free Plan - 20 requests/day (perfect for testing)
  • Starter Plan - 5,000 requests/day at $20/month
  • Pro Plan - 25,000 requests/day at $80/month
  • Business Plan - 50,000 requests/day at $200/month
  • Enterprise Plan - 200,000 requests/day at $500/month
  • Custom Plans - For projects with custom requirements

View full pricing details

Get Started Today

  1. Get your API key - Sign up for free
  2. Install the MCP server - Add the config to your AI assistant
  3. Start querying - Ask for news in natural language

Resources

Example: Building a News Briefing Bot

Here's a quick example of what you can build with the MCP server:

You: "Create a morning briefing with top headlines from 
technology, business, and world news"

AI: *Uses MCP to fetch from multiple categories*

"Good morning! Here's your briefing for December 8, 2024:

📱 TECHNOLOGY
- Major AI breakthrough announced by research team
- New smartphone features revealed at tech conference
- Cybersecurity alert issued for popular software

💼 BUSINESS  
- Stock markets react to economic data
- Tech giant announces quarterly earnings
- Merger talks confirmed between industry leaders

🌍 WORLD NEWS
- International summit concludes with new agreements
- Climate initiative gains momentum
- Breaking: Major development in ongoing situation

Would you like more details on any of these stories?"

Conclusion

The AllNewsAPI MCP Server bridges the gap between AI assistants and real-time news data. Whether you're a developer building news-powered applications, a researcher analyzing current events, or a content creator staying informed, the MCP server makes accessing news data as simple as asking a question.

Get started today:

  1. Sign up for AllNewsAPI
  2. Install the MCP server with npx allnewsapi-mcp@latest
  3. Start asking your AI assistant about current events

We can't wait to see what you build!

Have questions or feedback? Reach out to us at [email protected] or open an issue on GitHub.