# Wikipedia MCP Server

> Wikipedia MCP Server is an open-source MCP server for knowledge and memory. Search and read Wikipedia in any language: sections, references and nearby pages. It can run locally on your machine or as a hosted remote server.

- **Kind:** MCP server
- **Pricing:** Open source
- **Platforms:** CLI, self-hosted, API
- **Repository:** https://github.com/cyanheads/wikipedia-mcp-server
- **MCP Registry name:** io.github.cyanheads/wikipedia-mcp-server
- **Categories:** [knowledge and memory](https://ai-powered.com/categories/knowledge-and-memory), [web search and scraping](https://ai-powered.com/categories/web-search-and-scraping)
- **Listing updated:** 2026-11-18

## About

This server treats Wikipedia as structured data rather than a single page fetch. Search supports CirrusSearch operators such as incategory, morelike, intitle and insource, sorts by relevance or recency, and returns Wikidata IDs and spelling suggestions. Summaries include the page type, so a disambiguation page is flagged instead of returned as an answer.

For longer reading, a table-of-contents tool gives section indexes, and the article tool can fetch just one section. A reference tool lists footnotes in document order with their external links and DOIs. Geosearch finds geotagged articles near a coordinate, and a language tool lists the other editions of an article.

It runs over stdio or streamable HTTP, with a public hosted server, and ships a wikipedia-guide skill for switching editions and checking before reporting something as absent.

## Features

- **Operator-aware search:** Supports incategory, morelike, intitle, hastemplate and insource queries.
- **Section-level reads:** Fetch a single section using an index from the contents tool.
- **Cited references:** Lists footnotes with links, archive copies and DOIs.
- **Nearby articles:** Finds geotagged pages within a radius of coordinates.
- **Language editions:** Lists the language versions of an article with titles and URLs.

## Good for

- Pull a source-backed summary of a topic
- Read only the history section of a long article
- Collect the DOIs an article cites
- Find Wikipedia pages near a location
- Compare how an article differs across languages

## Install

### Claude Code (Terminal)

```sh
claude mcp add --transport http wikipedia-mcp-server https://wikipedia.caseyjhand.com/mcp
```

### Claude Desktop (Settings → Connectors → Add custom connector)

```sh
https://wikipedia.caseyjhand.com/mcp
```

### Cursor (~/.cursor/mcp.json)

```json
{
  "mcpServers": {
    "wikipedia-mcp-server": {
      "url": "https://wikipedia.caseyjhand.com/mcp"
    }
  }
}
```

### VS Code (.vscode/mcp.json)

```json
{
  "servers": {
    "wikipedia-mcp-server": {
      "type": "http",
      "url": "https://wikipedia.caseyjhand.com/mcp"
    }
  }
}
```

### Windsurf (~/.codeium/windsurf/mcp_config.json)

```json
{
  "mcpServers": {
    "wikipedia-mcp-server": {
      "serverUrl": "https://wikipedia.caseyjhand.com/mcp"
    }
  }
}
```

### Other clients (your client's MCP settings (most use this shape))

```json
{
  "mcpServers": {
    "wikipedia-mcp-server": {
      "type": "http",
      "url": "https://wikipedia.caseyjhand.com/mcp"
    }
  }
}
```

## Tools

- `wikipedia_search_articles`: Full-text search with ranked results, Wikidata QIDs and snippets.
- `wikipedia_get_summary`: Short summary for an article with description, thumbnail and coordinates.
- `wikipedia_get_article`: Full article or a targeted section as clean plain text.
- `wikipedia_get_sections`: Table of contents with section_index values.
- `wikipedia_search_nearby`: Geotagged articles within a radius of a coordinate.
- `wikipedia_get_languages`: Language editions available for an article.
- `wikipedia_get_references`: Footnotes an article cites, with links and DOIs.

## FAQ

### Does it cover other languages?

Yes, any Wikipedia language edition.

### How are disambiguation pages handled?

Summaries report a page type, and for disambiguation pages you re-query with search.

### How long can an article be?

Over the byte threshold (80,000 by default) it returns a section outline instead of the full text.

### Is there a hosted server?

Yes, at wikipedia.caseyjhand.com.

### Is Wikipedia MCP Server free?

Yes. Wikipedia MCP Server is open source, so you can use and self-host it for free.

### How do I add Wikipedia MCP Server to Claude Code?

Run this command in your terminal: claude mcp add --transport http wikipedia-mcp-server https://wikipedia.caseyjhand.com/mcp

### What are the best alternatives to Wikipedia MCP Server?

The closest alternatives to Wikipedia MCP Server are Scrapling MCP Server, Codebase Memory, XERJ, Firecrawl MCP Server and Claude Code Ultimate Guide.

## Where this comes from

- Description: written from the project's README.
- Install steps: from the official MCP Registry entry.

## Alternatives

- [Scrapling MCP Server](https://ai-powered.com/mcp/scrapling-mcp-server): Scrapling MCP Server is an open-source MCP server for web search and scraping.
- [Codebase Memory](https://ai-powered.com/mcp/codebase-memory): Codebase Memory is an open-source MCP server for knowledge and memory.
- [XERJ](https://ai-powered.com/mcp/xerj): XERJ is an open-source MCP server for knowledge and memory.
- [Firecrawl MCP Server](https://ai-powered.com/mcp/firecrawl-mcp-server): Firecrawl MCP Server is a freemium MCP server for web search and scraping.
- [Claude Code Ultimate Guide](https://ai-powered.com/mcp/claude-code-ultimate-guide): Claude Code Ultimate Guide is an open-source MCP server for ai models and llm tooling.
- [Douyin_TikTok_Download_API](https://ai-powered.com/mcp/douyin-tiktok-download-api): Douyin_TikTok_Download_API is an open-source MCP server for web search and scraping.
- [SearXNG Search](https://ai-powered.com/mcp/searxng-search): SearXNG Search is an open-source MCP server for web search and scraping.
- [Nautilus Compass Memory](https://ai-powered.com/mcp/nautilus-compass-memory): Nautilus Compass Memory is an open-source MCP server for knowledge and memory.

---
Source: https://ai-powered.com/mcp/wikipedia-mcp-server
