一个MCP服务器，连接LLM与《卫报》（自1999年起）档案，包括所有文章全文——超过190万篇。适用于实时头条新闻、新闻分析和历史研究。

安装

**需要Guardian开放平台API密钥。**你可以在这里获得：https://open-platform.theguardian.com/access/

《卫报》为档案的非商业使用提供慷慨的API访问权限，包括每秒最多1次通话和每天500次通话。（详见完整条款与条件。商业使用需另行许可。）

安装：

示例MCP客户端配置：

工具参考

guardian_search：在档案中搜索文章

使用detail_level参数确定API响应大小并优化性能：minimal（仅标题）、standard（标题、摘要和元数据）或full（所有内容，包括全文）。

guardian_get_article：检索单个条目

guardian_search_tags：搜索《卫报》超过5万个手工分配标签

guardian_find_related：通过共享标签查找与文章相似的文章

Guardian MCP Server

An MCP server that connects an LLM to the archives (since 1999) of The Guardian, including the full text of all articles — more than 1.9 million of them. Useful for real-time headlines, journalism analysis, and historical research.

Installation

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"
      }
    }
  }
}

Tool reference

guardian_search: search the archive for articles

Use thedetail_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
}

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; The Guardian’s API doesn’t natively return data to differentiate between Page 1 stories and inside briefs, and this tries to hack a ranking together

{
  "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

{