Guardian MCP Server

🚀 Guardian MCP Server

A server that connects an LLM to the archives (since 1999) of The Guardian, enabling real - time headlines, journalism analysis, and historical research.

🚀 Quick Start

The Guardian MCP Server connects an LLM to The Guardian's archives, containing over 1.9 million articles with full - text access. It's valuable for various research and analysis tasks.

✨ Features

• Connects to The Guardian's archives since 1999.
• Allows for real - time headlines, journalism analysis, and historical research.
• Offers multiple API endpoints for different types of searches and data retrieval.

📦 Installation

⚠️ Important Note

A Guardian Open Platform API key is required. You can get one here: https://open-platform.theguardian.com/access/. The Guardian offers generous API access for non - commercial use of the archives, including up to 1 call/second and 500 calls/day. (See the full Terms & Conditions. Commercial use requires a different license.)

To install:

npx guardian-mcp-server

Sample MCP client configuration:

{
  "mcpServers": {
    "guardian": {
      "command": "npx",
      "args": ["guardian-mcp-server"],
      "env": {
        "GUARDIAN_API_KEY": "your-key-here"
      }
    }
  }
}

💻 Usage Examples

Basic Usage

guardian_search: search the archive for articles

Use the detail_level parameter to determine the size of the API response and optimize performance: minimal (headlines only), standard (headlines, summaries, and metadata), or full (all content, including full article text).

{
  "query": "climate change",
  "section": "environment", 
  "detail_level": "minimal",
  "from_date": "2024-01-01",
  "order_by": "newest"
}

guardian_get_article: retrieve individual articles

{
  "article_id": "https://www.theguardian.com/politics/2024/dec/01/example", 
  "truncate": false  // full content by default
}

Advanced Usage

guardian_search_tags: search through The Guardian's 50,000 - plus hand - assigned tags

guardian_find_related: find articles similar to an article (via shared tags)

guardian_get_article_tags: returns tags assigned to any article

{
  "article_id": "politics/2024/example"
}

guardian_lookback: historical search by date

guardian_content_timeline: analyze Guardian content on a particular topic over a defined period

{
  "query": "artificial intelligence",
  "from_date": "2024-01-01",
  "to_date": "2024-06-30", 
  "interval": "month"
}

guardian_top_stories_by_date: estimates editorial importance

{
  "date": "2016-06-24",  // Brexit referendum day
  "story_count": 5
}

guardian_topic_trends: compare multiple topics over time with correlation analysis and competitive rankings

{
  "topics": ["artificial intelligence", "climate change", "brexit"],
  "from_date": "2023-01-01",
  "to_date": "2024-12-31",
  "interval": "quarter"
}

guardian_author_profile: generate profiles of Guardian journalists and what they cover

{
  "author": "George Monbiot",
  "analysis_period": "2024"
}

guardian_longread: search The Long Read series, the paper's home for longform features

guardian_browse_section: browse recent articles from specific sections

guardian_get_sections: fetch all available Guardian sections

guardian_search_by_length: filter articles by word count

guardian_search_by_author: search articles by byline

guardian_recommend_longreads: get personalized Long Read recommendations based on interest

{
  "count": 3,
  "context": "I'm researching technology, especially AI",
  "topic_preference": "digital culture"
}

📚 Documentation

Tool reference

This section provides details about each API endpoint provided by the Guardian MCP Server.

• guardian_search: Allows you to search the archive for articles. You can use the detail_level parameter to control the response size and optimize performance.
• guardian_get_article: Retrieves individual articles. By default, it returns the full content.
• guardian_search_tags: Searches through The Guardian's more than 50,000 hand - assigned tags.
• guardian_find_related: Finds articles similar to a given article through shared tags.
• guardian_get_article_tags: Returns the tags assigned to an article.
• guardian_lookback: Performs a historical search by date.
• guardian_content_timeline: Analyzes Guardian content on a particular topic over a defined period.
• guardian_top_stories_by_date: Estimates the editorial importance of articles.
• guardian_topic_trends: Compares multiple topics over time with correlation analysis and competitive rankings.
• guardian_author_profile: Generates profiles of Guardian journalists and their coverage.
• guardian_longread: Searches The Long Read series.
• guardian_browse_section: Browses recent articles from specific sections.
• guardian_get_sections: Fetches all available Guardian sections.
• guardian_search_by_length: Filters articles by word count.
• guardian_search_by_author: Searches articles by byline.
• guardian_recommend_longreads: Gets personalized Long Read recommendations based on interest.

📄 License

This project is released under the MIT license.