home / mcp / guardian mcp server

Guardian MCP Server

A MCP to connect LLMs to the archives of The Guardian

Installation

Add the following to your MCP client configuration file.

Configuration

{
  "mcpServers": {
    "jbenton-guardian-mcp-server": {
      "command": "npx",
      "args": [
        "guardian-mcp-server"
      ],
      "env": {
        "GUARDIAN_API_KEY": "YOUR_API_KEY"
      }
    }
  }
}

You can run a Guardian MCP Server to connect an LLM to The Guardian archives and access millions of articles via a simple MCP interface. This enables real-time headlines, journalism analysis, and rich historical research by querying The Guardian’s content through your language model pipelines.

How to use

Use the Guardian MCP Server to issue queries to The Guardian archives and retrieve metadata, headlines, summaries, or full articles for your AI workflows. You can search by keywords, dates, sections, and more, fetch individual articles, and explore related content or trends. Integrate the MCP endpoint into your client or application, then craft prompts that request the exact data you need, from quick headlines to full-text articles for analysis.

How to install

Prerequisites you need before installation are Node.js and npm on your machine.

Install and run the Guardian MCP Server with the following command.

npx guardian-mcp-server

Configure a client to connect to the running MCP server using the sample MCP client configuration below. Replace YOUR_API_KEY with your actual Guardian Open Platform API key.

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

Additional content

The Guardian MCP Server exposes a set of tools that you can use through your MCP client. Each tool corresponds to a specific API surface that you can call from your prompts to fetch data, articles, tags, timelines, and more. Ensure you provide your Guardian API key for access to the archives.

Available tools

guardian_search

Search the Guardian archive for articles with control over detail level to balance response size and content richness.

guardian_get_article

Retrieve an individual Guardian article by its identifier or URL, with options to truncate or return full content.

guardian_search_tags

Search through Guardian’s hand-assigned tags to categorize results and improve topic targeting.

guardian_find_related

Find articles similar to a given article by analyzing shared tags and overlap in topics.

guardian_get_article_tags

Return tags assigned to a specific Guardian article for tagging and later analysis.

guardian_lookback

Perform historical searches by date to explore content from a past period.

guardian_content_timeline

Analyze Guardian content on a topic over a defined time range and interval.

guardian_top_stories_by_date

Estimate editorial importance for a subset of stories by date when native ranking is insufficient.

guardian_topic_trends

Compare multiple topics over time using correlation analysis and rankings.

guardian_author_profile

Generate profiles of Guardian journalists and their coverage for a given period.

guardian_longread

Search The Guardian Long Read series for longform features.

guardian_browse_section

Browse recent articles from a specific Guardian section.

guardian_get_sections

Fetch all available Guardian sections.

guardian_search_by_length

Filter articles by word count to target concise or extensive content.

guardian_search_by_author

Search articles by byline to study a journalist’s output.

guardian_recommend_longreads

Provide personalized Long Read recommendations based on user interests.