Advertise
MCP.so
Sign In

MediaWiki MCP Server

@shiquda

Repository

Basic information

Category

Memory & Knowledge

Last updated

Transports

stdio

Author

shiquda

Submitted by

shiquda

About MediaWiki MCP Server

A MCP server that allows you to search and retrieve content on any wiki site using MediaWiki with LLMs 🤖 wikipedia.org, fandom.com, wiki.gg and more sites using Mediawiki are supported!

#wiki#mediawiki#wikipedia#mcp#mcp-server

MediaWiki MCP Server config

Add this server to your MCP-compatible client using the configuration below.

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

MediaWiki MCP Server tools

2

Search for a wiki page. The shorter the request, the better, preferably containing only the main term to be searched. Args: query: The query to search for limit: The number of results to return Returns: A list of pages that match the query

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

Overview

What is MediaWiki MCP Server?

An MCP server that provides seamless interaction with Wikipedia’s API, allowing you to search and retrieve Wikipedia content with LLMs.

How to use MediaWiki MCP Server?

Install uv, then configure your MCP client with uvx mediawiki-mcp-server. Set --base-url to the wiki site’s endpoint (defaults to https://en.wikipedia.org/w/). Available transports are stdio (default), streamable-http (port 8000), and SSE. Run uvx mediawiki-mcp-server --help for all options.

Key features of MediaWiki MCP Server

  • Search wiki pages with customizable wiki sites.
  • Retrieve detailed page content.
  • Supports any MediaWiki-based site (e.g., Wikipedia, Fandom, wiki.gg).
  • Multiple transport options: stdio, HTTP, SSE.
  • Configurable via command-line arguments.

Use cases of MediaWiki MCP Server

  • Add Wikipedia search capability to a chatbot or virtual assistant.
  • Retrieve full article text for summarization or question-answering.
  • Search across custom MediaWiki wikis (e.g., internal documentation).
  • Integrate wiki content extraction into agentic workflows.
  • Power knowledge-base lookup for LLM-powered tools.

Frequently asked questions

1

What does this server do?

It enables LLMs to search and retrieve content from any MediaWiki site (e.g., Wikipedia) by exposing two MCP tools: `search` and `get_page`.

2

How do I use a different wiki site?

Set the `--base-url` argument to the site’s API endpoint. Most MediaWiki endpoints follow `base-url/rest.php/v1/page`. Check by navigating to that URL in a browser.

3

What runtimes or dependencies are required?

Python 3.13 and the `uv` package manager. The server is run via `uvx mediawiki-mcp-server`.

4

Is this server outdated?

The README notes that this repository is outdated and directs users to [ProfessionalWiki/MediaWiki-MCP-Server](https://github.com/ProfessionalWiki/MediaWiki-MCP-Server) instead.

5

What transport options are available?

stdio (default), streamable-http (start with `--http`), and SSE (start with `--sse`). The default HTTP port is 8000.

Comments

More Memory & Knowledge MCP servers

HandbookHub MCP

veryayskiy

Search saved employee handbooks from your AI assistant. Four read-only tools list authorized handbooks, browse policies, search content, and read source pages with citation links. Uses scoped bearer tokens and Streamable

UmmahAPI

Yousuf Kazmi

Islamic source data for assistants: Quran, hadith, tafsir, duas, prayer times and qibla. Answers come from real sources with citations instead of recalled text, so verses and hadith are not hallucinated. 36,000+ hadiths

Stele

Stele-Dev

Shared memory for AI coding agents. Claude Code, Cursor and Codex read your project's decisions, lessons and tasks before they act.

ctxfile

ctxfile

Local-first MCP server that snapshots your project's working state into one context object. Open-core, privacy-first.

2

Konshus.AI

Konshus

Your own memory for every AI. Konshus brings in your ChatGPT, Claude, Gemini and Grok chats, notes and journals, and shares one private memory with Claude, ChatGPT, Cursor, Zed and more.

Advertise