About guardian-mcp-server
guardian-mcp-server helps researchers and readers search The Guardian's journalism archive from 1999 to the present, browse content, and retrieve full article text. Searches can be filtered by section, tag, contributor, and date.
Key features
- 01Search the full-text article archive
- 02Browse content by section or tag
- 03Retrieve article text and metadata
- 04Filter by contributor and date
- 05Discover available sections and tags
Use cases
- 01Research The Guardian's coverage of a topic
- 02Find articles by contributor or date
- 03Browse recent content in a section or tag
MCP support
Exposes article search, retrieval, and content-browsing tools to MCP clients over STDIO or Streamable HTTP; a Guardian Open Platform API key is required.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
npx -y @cyanheads/guardian-mcp-serverGUARDIAN_API_KEYSecretAPI key for The Guardian Open Platform (https://open-platform.theguardian.com/).MCP_LOG_LEVELSets the minimum log level for output (e.g., 'debug', 'info', 'warn').MCP_TRANSPORT_TYPESelects the HTTP transport.MCP_HTTP_HOSTThe hostname for the HTTP server.MCP_HTTP_PORTThe port to run the HTTP server on.MCP_HTTP_ENDPOINT_PATHThe endpoint path for the MCP server.MCP_AUTH_MODESecretAuthentication mode to use: 'none', 'jwt', or 'oauth'.Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.
Tools
3Saved tool list · updated 2w ago
| Parameter | Type | Required | Description |
|---|---|---|---|
| tag | string | No | Restrict to content carrying this tag ID (e.g. "environment/climate-change", "technology/artificial-intelligence", "world/ukraine"). Multiple tags separated by commas apply AND logic. Use guardian_browse with mode=list_tags to discover valid tag IDs. |
| page | integer | No | Page number (1-indexed). Each page returns up to page_size results. |
| query | string | Yes | Full-text search query. Supports AND, OR, NOT operators and exact phrases in double quotes. Example: "climate change" AND (policy OR legislation) |
| section | string | No | Restrict results to a section ID (e.g. "world", "politics", "science", "environment", "technology", "culture", "sport", "lifeandstyle"). Use guardian_browse with mode=list_sections to discover valid section IDs. |
| to_date | string | No | Return only articles published on or before this date. Format: YYYY-MM-DD (e.g. "2024-03-31"). |
| order_by | enum | No | Sort order. "relevance" ranks by match strength (default when a query is provided). "newest" and "oldest" sort by publication date.newest | oldest | relevance |
| from_date | string | No | Return only articles published on or after this date. Format: YYYY-MM-DD (e.g. "2024-01-15"). |
| page_size | integer | No | Number of results per page (1–50). Keep low (≤10) when requesting full body text to manage context size. Large bodies can be 10–30KB each. |
| contributor | string | No | Restrict to articles by this contributor tag ID (e.g. "profile/george-monbiot"). Contributor IDs follow the pattern "profile/<slug>". Use guardian_browse with mode=list_tags and tag_type=contributor to discover contributor IDs. |
Details
From the project README@cyanheads/guardian-mcp-server
Search, browse, and retrieve full article text from The Guardian's journalism archive (1999–present) via MCP. STDIO or Streamable HTTP.
Overview
The Guardian's journalism archive, 1999 to today. Search full text, browse by section or tag, and fetch individual articles.
Tools
| Tool | Description |
|---|---|
guardian_search_articles | Full-text search across The Guardian's archive with optional section, tag, contributor, and date filters |
guardian_get_article | Fetch a single Guardian article by ID with body text and metadata |
guardian_browse_content | Browse by section or tag, or discover available sections and tags, across four modes |
Capability reference
guardian_search_articles tool
- Boolean
querysyntax (AND/OR/NOT, quoted phrases), optionalsection/tag/contributorandfrom_date/to_date(YYYY-MM-DD) filters;order_by:relevance(default),newest, oroldest;page+page_size(1–50, default 10) - Articles carry metadata, HTML-stripped body text and a
truncatedflag; results includetotal,page,pages,page_size, andorder_by - Fails with
no_resultsorinvalid_date(dates must be real calendar dates) tagaccepts comma (AND), pipe|(OR), hyphen-(NOT), and parentheses, e.g.environment/climate-crisis|environment/flooding. Wrap an OR expression in parentheses when also passingcontributor.
guardian_get_article tool
- Required
article_id: the path-slugidreturned byguardian_search_articlesorguardian_browse_content - Returns HTML-stripped body text, metadata, contributors, pillar/section classification, and
truncated - Fails with
not_found
guardian_browse_content tool
- Four
modevalues:section_latest(requiressection_id),tag_latest(requirestag_id),list_sections,list_tags;page+page_size(1–50, default 10) for articles and tags list_tagsfilters by optionalqueryandtag_type(keyword,contributor,blog,series,tone,type,publication,newspaper-book,newspaper-book-section); output carriesmode,total, and the matchingresults/sections/tagsarray- Fails with
missing_section_id,missing_tag_id,section_not_found, ortag_not_found.tag_idaccepts the same boolean expressions as search'stag.
All three tools also fail with status-specific HTTP errors. Not retryable: unauthorized (401), access_denied (403), request_rejected (400), validation_failed (422), invalid_request, request_conflict, request_not_found, and api_unsupported (501). Retryable: api_timeout (408/425/504), rate_limited (429), and api_error (other 5xx). Each error carries a recovery hint.
Features
Built on @cyanheads/mcp-ts-core: stdio and Streamable HTTP transports, pluggable auth (none / jwt / oauth), swappable storage (in-memory, filesystem, Supabase, Cloudflare KV/R2/D1), structured logging with optional OpenTelemetry tracing.
Guardian-specific:
- Wraps the Guardian Open Platform API with a free non-commercial developer key
- Full body text extraction — HTML stripped, not just headlines or abstracts
- Contributor ID discovery via
guardian_browse_contentmodelist_tagswithtag_type=contributor - Section and tag taxonomy browsing (
list_sections,list_tags) for filter discovery before searching - Free tier: 5,000 requests/day, 12 calls/second — the server applies no additional throttling
Agent-friendly output:
- Search and article-returning browse modes cap previews at 2,000 words and set
truncated; callguardian_get_articlefor the full text - Typed error reasons across all three tools, each paired with a recovery hint
total/page/pageson every paginated response so callers can track result scope
Getting started
Add the following to your MCP client configuration file. Register for a free Guardian Open Platform API key at open-platform.theguardian.com/access.
{
"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/mcp
Prerequisites
- Bun v1.4.0 or higher (or Node.js v24+).
- A free Guardian Open Platform API key — register at 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.git
- Navigate into the directory:
cd guardian-mcp-server
- Install dependencies:
bun install
- Configure environment:
cp .env.example .env
# Edit .env and set GUARDIAN_API_KEY
Configuration
| Variable | Description | Default |
|---|---|---|
GUARDIAN_API_KEY | Required. Free developer key from open-platform.theguardian.com/access. | — |
MCP_TRANSPORT_TYPE | Transport: stdio or http. | stdio |
MCP_HTTP_PORT | Port for HTTP server. | 3010 |
MCP_SESSION_MODE | HTTP session mode: stateless, stateful, or auto (resolves to stateful). The server declares stateless; an exported value overrides it. | stateless |
MCP_AUTH_MODE | Auth mode: none, jwt, or oauth. | none |
MCP_LOG_LEVEL | Log level (RFC 5424). | info |
LOGS_DIR | Directory for log files (Node.js only). | <project-root>/logs |
LOG_TOOL_FAILURE_PAYLOADS | Log failed tool arguments and results, redacted by key name and capped by LOG_TOOL_FAILURE_PAYLOAD_MAX_BYTES (default 16384). Secrets in free-form values remain visible. | false |
STORAGE_PROVIDER_TYPE | Storage backend. | in-memory |
OTEL_ENABLED | Enable OpenTelemetry instrumentation (spans, metrics, completion logs). | false |
OTEL_EXPORTER_OTLP_ENDPOINT | Base OTLP URL; traces use /v1/traces, metrics use /v1/metrics. | — |
OTEL_EXPORTER_OTLP_LOGS_ENDPOINT | Opt-in OTLP log endpoint, used as-is. | — |
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:http -
Run 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-server
The 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 |
|---|---|
src/index.ts | createApp() entry point — registers tools and initializes the Guardian service. |
src/config | Server-specific environment variable parsing (GUARDIAN_API_KEY). |
src/mcp-server/tools | Tool definitions (*.tool.ts): guardian_search_articles, guardian_get_article, guardian_browse_content. |
src/services/guardian | Guardian Open Platform API client, normalization, and type definitions. |
tests/ | Unit and integration tests. |
docs/ | 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 logic - Use
ctx.logfor request-scoped logging,ctx.statefor tenant-scoped storage - Register new tools in the
createApp()toolsarray insrc/index.ts - Wrap external API calls: validate raw → normalize to domain type → return output schema; never fabricate missing fields
Contributing
Issues are welcome. Run checks and tests before submitting:
bun run devcheck
bun run test
License
Apache-2.0 — see LICENSE for details.
Powered by The Guardian.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.