@cyanheads/guardian-mcp-server
Provides tools for searching, browsing, and retrieving full article text from The Guardian's journalism archive (1999–present), including full-text search with filters, single article retrieval, and content browsing by section or tag.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@@cyanheads/guardian-mcp-serversearch for articles about climate change from 2023"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Prerequisites
A free Guardian Open Platform API key is required. Register at https://open-platform.theguardian.com/access — the non-commercial developer tier is free. Set it as
GUARDIAN_API_KEYin your MCP client config or.envfile. The server will not start without it.Rate limits (free tier): 5,000 requests/day, 12 calls/second. The server applies no additional throttling — stay within these bounds.
Related MCP server: Guardian News MCP Server
Tools
Three tools for working with The Guardian's journalism archive:
Tool | Description |
| Full-text search across The Guardian's archive (1999–present) with optional section, tag, contributor, and date filters. Returns articles with full body text (HTML stripped, truncated at 2,000 words). |
| Fetch a single Guardian article by its ID (path slug) with full body text and all metadata. Use after |
| Browse The Guardian's content by section or tag, or discover available sections and tags. Four modes: |
guardian_search
Full-text search with structured filters across the entire Guardian archive.
Supports AND, OR, NOT boolean operators and exact phrases in double quotes
Filters: section ID, tag ID, contributor profile ID, date range (
from_date,to_date)Returns body text (HTML stripped) truncated at 2,000 words with a truncation flag — use
guardian_get_articlefor complete textSort by
relevance(default),newest, oroldestPagination via
page+page_size(1–50 per page)
guardian_get_article
Fetch one article by its Guardian path-slug ID.
Input:
article_idfromguardian_searchresults — theidfield, e.g."world/2024/mar/01/ukraine-war-latest"Returns complete untruncated body text (HTML stripped), full metadata, contributor list, and pillar/section classification
truncated: truein the response means the body still exceeded 2,000 words after fetching
guardian_browse
Browse and discover Guardian content — four modes in one tool.
section_latest: newest articles from a section (requiressection_id)tag_latest: newest articles carrying a tag (requirestag_id)list_sections: returns all Guardian sections as a flat list — use to discover validsection_idvalueslist_tags: searches the tag taxonomy with optionalqueryandtag_typefilter — use to discover contributor IDs (tag_type=contributor), keyword tags, series, and morePagination applies to all modes
Features
Built on @cyanheads/mcp-ts-core:
Declarative tool definitions — single file per tool, framework handles registration and validation
Unified error handling — handlers throw, framework catches, classifies, and formats
Pluggable auth:
none,jwt,oauthSwappable storage backends:
in-memory,filesystem,Supabase,Cloudflare KV/R2/D1Structured logging with optional OpenTelemetry tracing
STDIO and Streamable HTTP transports
Guardian-specific:
Wraps the Guardian Open Platform API with a free developer key
Full body text extraction — HTML stripped, not just headlines or abstracts
Contributor ID discovery via
guardian_browsemodelist_tags+tag_type=contributorSection and tag taxonomy browsing for filter discovery before searching
Powered by The Guardian
Agent-friendly output:
Truncation flags on every article — agents know whether to call
guardian_get_articlefor the restTyped error reasons (
unauthorized,no_results,not_found,invalid_date,api_error) with recovery hints for each casetotal,page, andpageson all paginated responses so agents can communicate result scopeZero-result enrichment notice on
guardian_search— echoes the query and suggests how to broaden
Getting started
A
GUARDIAN_API_KEYis required. Register for the free non-commercial developer key at https://open-platform.theguardian.com/access.
Add the following to your MCP client configuration file:
{
"mcpServers": {
"guardian-mcp-server": {
"type": "stdio",
"command": "bunx",
"args": ["@cyanheads/guardian-mcp-server@latest"],
"env": {
"MCP_TRANSPORT_TYPE": "stdio",
"MCP_LOG_LEVEL": "info",
"GUARDIAN_API_KEY": "your-api-key"
}
}
}
}Or with npx (no Bun required):
{
"mcpServers": {
"guardian-mcp-server": {
"type": "stdio",
"command": "npx",
"args": ["-y", "@cyanheads/guardian-mcp-server@latest"],
"env": {
"MCP_TRANSPORT_TYPE": "stdio",
"MCP_LOG_LEVEL": "info",
"GUARDIAN_API_KEY": "your-api-key"
}
}
}
}Or with Docker:
{
"mcpServers": {
"guardian-mcp-server": {
"type": "stdio",
"command": "docker",
"args": [
"run", "-i", "--rm",
"-e", "MCP_TRANSPORT_TYPE=stdio",
"-e", "GUARDIAN_API_KEY=your-api-key",
"ghcr.io/cyanheads/guardian-mcp-server:latest"
]
}
}
}For Streamable HTTP, set the transport and start the server:
MCP_TRANSPORT_TYPE=http MCP_HTTP_PORT=3010 GUARDIAN_API_KEY=your-api-key bun run start:http
# Server listens at http://localhost:3010/mcpPrerequisites
Bun v1.3.0 or higher (or Node.js v24+).
A free Guardian Open Platform API key — register at https://open-platform.theguardian.com/access. The non-commercial developer tier is free and instant.
Installation
Clone the repository:
git clone https://github.com/cyanheads/guardian-mcp-server.gitNavigate into the directory:
cd guardian-mcp-serverInstall dependencies:
bun installConfigure environment:
cp .env.example .env
# Edit .env and set GUARDIAN_API_KEYConfiguration
Variable | Description | Default |
| Required. Free developer key from open-platform.theguardian.com/access. | — |
| Transport: |
|
| Port for HTTP server. |
|
| Auth mode: |
|
| Log level (RFC 5424). |
|
| Directory for log files (Node.js only). |
|
| Storage backend. |
|
| Enable OpenTelemetry instrumentation (spans, metrics, completion logs). |
|
See .env.example for the full list of optional overrides.
Running the server
Local development
Build and run:
# One-time build bun run rebuild # Run the built server bun run start:stdio # or bun run start:httpRun checks and tests:
bun run devcheck # Lint, format, typecheck, security bun run test # Vitest test suite bun run lint:mcp # Validate MCP definitions against spec
Docker
docker build -t guardian-mcp-server .
docker run --rm -e GUARDIAN_API_KEY=your-api-key -p 3010:3010 guardian-mcp-serverThe Dockerfile defaults to HTTP transport, stateless session mode, and logs to /var/log/guardian-mcp-server. OpenTelemetry peer dependencies are installed by default — build with --build-arg OTEL_ENABLED=false to omit them.
Project structure
Directory | Purpose |
|
|
| Server-specific environment variable parsing ( |
| Tool definitions ( |
| Guardian Open Platform API client, normalization, and type definitions. |
| Unit and integration tests. |
| Design document and directory tree. |
Development guide
See CLAUDE.md / AGENTS.md for development guidelines and architectural rules. The short version:
Handlers throw, framework catches — no
try/catchin tool logicUse
ctx.logfor request-scoped logging,ctx.statefor tenant-scoped storageRegister new tools via the barrel in
src/mcp-server/tools/definitions/index.tsWrap external API calls: validate raw → normalize to domain type → return output schema; never fabricate missing fields
Contributing
Issues and pull requests are welcome. Run checks and tests before submitting:
bun run devcheck
bun run testLicense
Apache-2.0 — see LICENSE for details.
Powered by The Guardian.
This server cannot be deployed
Maintenance
Related MCP Connectors
Web search, scraping, RAG answers with citations, and translation as MCP tools.
Search the agentic web. 4,100+ sites, 11 tools incl. check_url + verify_mcp for probe-before-use.
Web Content Extract Mcp connects AI agents to real public APIs via MCP. Tools include
Scrape, crawl and search the web for AI agents via MCP.
Related MCP Servers
- AlicenseBqualityDmaintenanceProvides access to the complete archives of The Guardian newspaper since 1999, including the full text of 1.9 million articles.1655 npm20MIT
- FlicenseNot gradedqualityDmaintenanceEnables users to search for the latest news articles from The Guardian using keywords and check service status. Provides access to Guardian's news content through their API with configurable result limits.1-
- AlicenseNot gradedqualityBmaintenanceEnables searching and retrieving articles, sections, and tags from The Guardian via the Guardian Open Platform API.MIT
- AlicenseAqualityCmaintenanceThree practical MCP tools to investigate agents, threads, and content trust signals.301MIT