The Guardian MCP server

Integrates with The Guardian's Open Platform API to search articles, retrieve full content, browse sections, and perform analytical operations like author profiling and topic trend analysis with 17 specialized tools including Long Read discovery and content timeline analysis.
Back to servers
Setup instructions
Provider
Joshua Benton
Release date
Jun 29, 2025
Language
Go
Stats
16 stars

The Guardian MCP Server connects your language model to the complete archives of The Guardian newspaper, giving you access to the full text of more than 1.9 million articles dating back to 1999. This tool is valuable for real-time headlines, journalism analysis, and historical research.

Installation Requirements

Before installing, you need to obtain a Guardian Open Platform API key from their access page.

For non-commercial use, The Guardian offers generous API access with limits of 1 call/second and 500 calls/day. Commercial use requires a different license.

Installation

To install the server, run:

npx guardian-mcp-server

Configuration

When setting up your MCP client, use the following configuration format:

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

Available Tools

Search and Retrieval

guardian_search

Search the archive for articles with various filtering options:

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

The detail_level parameter optimizes performance:

  • minimal: headlines only
  • standard: headlines, summaries, and metadata
  • full: all content, including full article text

guardian_get_article

Retrieve individual articles:

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

Tag Management

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"
}

Historical and Timeline Analysis

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 of stories on a specific date:

{
  "date": "2016-06-24",
  "story_count": 5
}

Content Analysis

guardian_topic_trends

Compare multiple topics over time with correlation analysis:

{
  "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 their coverage areas:

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

Specialized Content Access

guardian_longread

Search The Long Read series 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:

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

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "guardian" '{"command":"npx","args":["guardian-mcp-server"],"env":{"GUARDIAN_API_KEY":"your-key-here"}}'

See the official Claude Code MCP documentation for more details.

For Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

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

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

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

2. Add this to your configuration file:

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

3. Restart Claude Desktop for the changes to take effect

Want to 10x your AI skills?

Get a free account and learn to code + market your apps using AI (with or without vibes!).

Nah, maybe later