Skip to main content
Glama
mediawiki-mcp-server

mediawiki-mcp-server

by shiquda

Outdated. Please use https://github.com/ProfessionalWiki/MediaWiki-MCP-Server instead!

MediaWiki MCP Server 🚀

A MCP server that provides seamless interaction with Wikipedia's API. This tool allows you to search and retrieve Wikipedia content with LLMs 🤖!

https://github.com/user-attachments/assets/b5d9c5f3-a60e-48ea-8b4b-f1a7524d4fbb

Features ✨

  • 🔍 Search wiki pages with customizable wiki site. e.g. wikipedia.org, fandom.com, wiki.gg and more!

  • 📖 Retrieve detailed page content

Related MCP server: mediawiki-mcp-server

Usage 💻

  1. Ensure that uv is installed on your device.

  2. Configure in your client:

The server defaults to using https://en.wikipedia.org/. Also, you can make the server search other wiki sites!

To see if a wiki site works with this server, check if it uses MediaWiki software (usually shown by an icon at the bottom of the site).

To check further and find the endpoint (usually the website's domain, like https://mediawiki.org/), check by going to base-url/rest.php/v1/page in a browser (like https://noita.wiki.gg/rest.php/v1/page) and see if the output looks right. If not, add '/w' to the base URL and try again.

Then, set this endpoint as --base-url:

Available transports: stdio (default), streamable-http (http://localhost/mcp), and SSE (http://localhost/sse). See -h for all options.

uvx mediawiki-mcp-server --h
usage: main.py [-h] [--base-url BASE_URL] [--http] [--sse] [--port PORT]

MediaWiki MCP Server

options:
  -h, --help           show this help message and exit
  --base-url BASE_URL  Base URL for the MediaWiki API (default: https://en.wikipedia.org/w/``)
  --http               Run server as streamable-http (instead of stdio)
  --sse                Run server as sse-http (instead of stdio)
  --port PORT          Default port for http transport (default: 8000)

Example JSON configurations:

{
  "mcpServers": {
    "mediawiki-mcp-server": {
      "command": "uvx",
      "args": [
        "mediawiki-mcp-server",
        "--base-url", "https://example.com/"
      ],
      "env": {
        "HTTP_PROXY": "http://example.com:port"
      }
    }
  }
}

Or, if you want to run this server from source:

{
  "mcpServers": {
    "mediawiki-mcp-server": {
      "command": "uv",
      "args": [
        "run",
        "--directory", 
        "mediawiki-mcp-server",
        "path/to/project/src/mediawiki_mcp_server",
        "--base-url", "https://example.com/"
      ],
      "env": {
        "HTTP_PROXY": "http://example.com:port"
      }
    }
  }
}

Supported Tools 🛠

  • query: Search term (preferably short and focused)

  • limit: Maximum number of results to return (default: 5)

Get Page

  • title: The exact title of the Wikipedia page to retrieve

Development 👨‍💻

npx @modelcontextprotocol/inspector uv run mediawiki-mcp-server

Here are some documents that might help:

Contributing 🤝

This server is under development. Contributions are welcome! Feel free to submit issues and pull requests.

  • Cherry Studio: A desktop client that supports for multiple LLM providers. MCP is supported.

Available Tools

2 tools
get_pageB

Get a page from mediawiki.org Args: title: The title of the page to get, which can be found in title field of the search results Returns: The page content

Inputs: title (required).

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    B3.3/5.0

    Scored across 2 tools

    Disambiguation5/5

    The two tools have clearly distinct purposes: get_page retrieves specific page content by title, while search finds pages matching a query. There is no overlap in functionality, making it easy for an agent to select the correct tool based on the task.

    Naming Consistency5/5

    Both tools follow a consistent verb_noun pattern (get_page and search, where search implies 'search_pages'). The naming is simple, predictable, and uses snake_case uniformly, providing clear readability.

    Tool Count2/5

    With only 2 tools, the server feels thin for a MediaWiki domain, lacking essential operations like creating, updating, or deleting pages. While get_page and search cover basic retrieval, the scope is incomplete, making it borderline too few for practical use.

    Completeness2/5

    The tool surface is severely incomplete for a MediaWiki server, missing core CRUD operations (e.g., create_page, update_page, delete_page) and other common actions like listing categories or handling user interactions. This will likely cause agent failures in broader workflows.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      D
      maintenance
      An MCP server for Wiki.js projects that enables full-text search, page retrieval, and page management capabilities. It allows LLMs to interact with wiki content through specialized tools for searching, listing, and creating pages.
      ISC
    • A
      license
      Not graded
      quality
      D
      maintenance
      MCP server for persistent, compounding markdown wikis maintained by LLMs. Enables incremental knowledge base building with interlinked pages, search, and raw source management.
      34 npm
      1
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      MCP server that provides tools to add to, search, and manage a wiki knowledge base, enabling AI chat tools to contribute and retrieve information from the wiki via natural language prompts.
      MIT