Wikipedia Mcp Server

---

Tools

Six tools for working with Wikipedia across all language editions:

Tool	Description
wikipedia_search	Full-text search across Wikipedia, returning ranked results with plain-text snippets and page IDs.
wikipedia_get_summary	Lead-section summary for any article — plain text, Wikidata QID, description, thumbnail URL, and page type.
wikipedia_get_article	Full article or a targeted section as clean plain text, with section markers preserved.
wikipedia_get_sections	Table of contents with section_index values for targeted section reads.
wikipedia_search_nearby	Geotagged Wikipedia articles within a radius of a WGS 84 coordinate, sorted by distance.
wikipedia_get_languages	All language editions available for an article, with titles and URLs.

wikipedia_search

Search Wikipedia articles by full-text query.

• Returns ranked results with plain-text snippets (HTML stripped), page IDs, and word counts
• Use when the exact article title is unknown or to discover multiple articles on a topic
• Page beyond the first result page with offset; the enrichment nextOffset signals more results remain (pass it back as offset)
• Supports all Wikipedia language editions via the language parameter

---

wikipedia_get_summary

Fetch the lead-section summary for a Wikipedia article.

• Returns the 2–4 paragraph intro, Wikidata QID for cross-referencing, short description, and thumbnail URL
• Surfaces page_type: "disambiguation" — a signal to follow up with wikipedia_search using a more specific query
• Redirect pages followed automatically
• Right tool for 90% of encyclopedic lookups

---

wikipedia_get_article

Fetch article content as clean plain text.

• Without section_index: returns the full article with == Section == markers — unless it exceeds WIKIPEDIA_ARTICLE_OVERFLOW_BYTES (default 80 KB), in which case it returns a compact section outline (truncated: true) pointing to wikipedia_get_sections plus a section_index read
• With section_index (from wikipedia_get_sections): returns that section together with every subsection nested under it, each heading above its own body
• Data tables and figures are omitted from both paths, so a section whose body is entirely a data table returns its heading and little else. Tables used only for layout — multi-column lists, succession boxes — keep their content
• Page furniture is omitted too: maintenance banners, sister-project and library-resource boxes, portal bars, and spoken-article notices. Hatnotes are kept — they name the article to read next
• Redirect pages followed automatically

---

wikipedia_get_sections

Fetch the table of contents for a Wikipedia article.

• Returns section titles, heading levels, section numbering (e.g. "2.1"), and section_index values
• section_index is the integer to pass to wikipedia_get_article for targeted reads
• Call this before wikipedia_get_article when only a specific section is needed
• Redirect pages followed automatically

---

wikipedia_search_nearby

Find Wikipedia articles about places near a geographic coordinate.

• Results sorted ascending by distance in meters
• Only articles with geographic coordinates in their Wikidata record are returned
• Radius capped at 10,000 meters; up to 50 results per call

---

wikipedia_get_languages

List language editions available for a Wikipedia article.

• Returns each edition's language code, tool-usable subdomain code (edition_code), article title, and URL
• Pass edition_code as the language parameter on other tools — it can differ from language_code (e.g. gsw vs als)
• Use for cross-language research or to discover a non-English title before switching editions

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, oauth
• Swappable storage backends: in-memory, filesystem, Supabase, Cloudflare KV/R2/D1
• Structured logging with optional OpenTelemetry tracing
• STDIO and Streamable HTTP transports

Wikipedia-specific:

• Dual API integration — MediaWiki REST API (/api/rest_v1/) for summaries, Action API (/w/api.php) for search, full text, sections, geo search, and language links
• Retry and backoff on all requests; User-Agent header per Wikimedia API policy
• Both read paths render to the same plain-text shape — == Heading == markers, one list item per line — the full article from Action API extracts, a section from the parser's own HTML for that section. A section read additionally keeps code-sample indentation and the lists inside layout tables, neither of which the extract carries
• Per-call language parameter on every tool — all Wikipedia language editions accessible in a single session
• Language validation against a live edition registry built from the MediaWiki action=sitematrix endpoint (cached 24h) — catches structurally valid but nonexistent editions before they cause timeouts

Agent-friendly output:

• page_type field on summaries discriminates article / disambiguation / redirect — no string parsing needed
• wikibase_item (Wikidata QID) on summaries enables direct cross-referencing with wikidata-mcp-server
• section_index on table-of-contents entries links directly to the targeted-read parameter on wikipedia_get_article
• Recovery hints on every error type — callers get actionable next steps (e.g., "use wikipedia_search to find the correct title")

Getting started

Add the following to your MCP client configuration file.

{
  "mcpServers": {
    "wikipedia-mcp-server": {
      "type": "stdio",
      "command": "bunx",
      "args": ["@cyanheads/wikipedia-mcp-server@latest"],
      "env": {
        "MCP_TRANSPORT_TYPE": "stdio",
        "MCP_LOG_LEVEL": "info"
      }
    }
  }
}

Or with npx (no Bun required):

{
  "mcpServers": {
    "wikipedia-mcp-server": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "@cyanheads/wikipedia-mcp-server@latest"],
      "env": {
        "MCP_TRANSPORT_TYPE": "stdio",
        "MCP_LOG_LEVEL": "info"
      }
    }
  }
}

Or with Docker:

{
  "mcpServers": {
    "wikipedia-mcp-server": {
      "type": "stdio",
      "command": "docker",
      "args": [
        "run", "-i", "--rm",
        "-e", "MCP_TRANSPORT_TYPE=stdio",
        "ghcr.io/cyanheads/wikipedia-mcp-server:latest"
      ]
    }
  }
}

For Streamable HTTP, set the transport and start the server:

MCP_TRANSPORT_TYPE=http MCP_HTTP_PORT=3010 bun run start:http
# Server listens at http://localhost:3010/mcp

Prerequisites

• Bun v1.3.0 or higher (or Node.js v24+).
• No API keys required — Wikipedia's API is public.

Installation

1. Clone the repository:

git clone https://github.com/cyanheads/wikipedia-mcp-server.git

2. Navigate into the directory:

cd wikipedia-mcp-server

3. Install dependencies:

bun install

4. Configure environment (optional):

cp .env.example .env
# edit .env if you want to customize WIKIPEDIA_USER_AGENT or logging

Configuration

Variable	Description	Default
WIKIPEDIA_USER_AGENT	User-Agent header sent with every Wikimedia API request. Customize for your deployment.	wikipedia-mcp-server/0.1.17 (https://github.com/cyanheads/wikipedia-mcp-server)
WIKIPEDIA_BASE_URL	Optional single-instance override. Unset (default): compose per-language hosts, language selects the edition per call. Set to a full base URL (e.g. a private MediaWiki mirror): route every call at that one fixed host — language no longer varies it.	(unset)
WIKIPEDIA_ARTICLE_OVERFLOW_BYTES	Byte budget above which a full-article read (wikipedia_get_article without section_index) returns a section outline instead of the full text. Tuned for this domain — ordinary articles stay whole; only genuine mega-articles (World War II ~86 KB, United States ~94 KB) outline. Section-targeted reads are never affected.	80000
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 (which resolves to stateful). The Docker image ships stateless.	auto
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
OTEL_ENABLED	Enable OpenTelemetry instrumentation (spans, metrics, completion logs).	false

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 wikipedia-mcp-server .
docker run --rm -p 3010:3010 wikipedia-mcp-server

The Dockerfile defaults to HTTP transport, stateless session mode, and logs to /var/log/wikipedia-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 inits the Wikipedia service.
src/config	Server-specific environment variable parsing and validation with Zod.
src/mcp-server/tools	Tool definitions (*.tool.ts) — one file per tool.
src/services/wikipedia	WikipediaService — REST API + Action API client with retry/backoff and language validation.
tests/	Unit and integration tests mirroring src/.

Development guide

See CLAUDE.md for development guidelines and architectural rules. The short version:

• Handlers throw, framework catches — no try/catch in tool logic
• Use ctx.log for request-scoped logging, ctx.state for tenant-scoped storage
• Register new tools in src/mcp-server/tools/definitions/index.ts
• Wrap 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 test

License

Apache-2.0 — see LICENSE for details.