MediaWiki MCP Server
Interact with the MediaWiki API to search and retrieve content from Wikipedia or other MediaWiki sites.
Outdated.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
Usage 💻
- Ensure that uv is installed on your device.
- 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 🛠
Search
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.
Related Projects ♥️
- Cherry Studio: A desktop client that supports for multiple LLM providers. MCP is supported.
Máy chủ liên quan
Context7 HTTP
An MCP server for the Context7 project, providing HTTP streaming and search endpoints for library information without local installation.
SearxNG MCP Server
Provides web search capabilities using a self-hosted SearxNG instance, allowing AI assistants to search the web.
Gemini Search
Generates responses using the Gemini API and Google Search for up-to-date information.
Brave Search
An MCP server for web and local search using the Brave Search API.
Library Docs MCP Server
Search and fetch documentation for popular libraries like Langchain, Llama-Index, and OpenAI using the Serper API, providing updated information for LLMs.
Legislative Yuan API
Search for bills, documents, and meeting records from Taiwan's Legislative Yuan API.
Glean
Search and chat across your company's apps using the Glean API.
O'Reilly Learning Platform
Search and manage content on the O'Reilly Learning Platform.
o3 Search
Web search using OpenAI's o3 model. Requires an OpenAI API key.
Image Sorcery
At Sunrise Apps, we believe AI agents should be limitless, especially when it comes to visual data. We created ImageSorcery to bridge the critical gap in AI's ability to interact with and manipulate images directly, all while upholding the highest standards of privacy and security.
