MediaWiki
Model Context Protocol (MCP) Server to connect your AI with any MediaWiki
claude mcp add --transport stdio professionalwiki-mediawiki-mcp-server npx @professional-wiki/mediawiki-mcp-server@latest \ --env CONFIG="path/to/config.json"
How to use
This MCP server exposes MediaWiki access through a set of MCP tools that allow a client (such as an LLM) to interact with one or more MediaWiki wikis. Core capabilities include adding and removing wikis, creating, editing, deleting, and retrieving pages, as well as accessing page history, revisions, and files. The server supports both public and authenticated operations; tools marked with a lock emoji require authentication via OAuth2 tokens or bot credentials as configured in your wiki configuration. Use the add-wiki tool to register a wiki resource, then perform actions like create-page, update-page, upload-file, and search-page to read and mutate wiki content. The response formats follow the standard MCP conventions, returning structured JSON for resource listings, page data, and revision history.
How to install
Prerequisites:
- Node.js and npm installed on your machine
- Access to the internet to fetch packages
- Optional: a configured config.json for private wikis if needed
Install via Smithery (automatic):
npx -y @smithery/cli install @ProfessionalWiki/mediawiki-mcp-server --client claude
Install in Claude Desktop (example configuration):
{
"mcpServers": {
"mediawiki-mcp-server": {
"command": "npx",
"args": [
"@professional-wiki/mediawiki-mcp-server@latest"
],
"env": {
"CONFIG": "path/to/config.json"
}
}
}
}
Install in VS Code (add MCP server):
# Using the provided command from the README extension snippet
Install in Cursor or Windsurf follows the same pattern: use npx with the latest package name and provide a path to your config via the CONFIG environment variable, for example:
npx @professional-wiki/mediawiki-mcp-server@latest
Notes:
- Ensure your config.json (or config.json path) is accessible and properly formatted before starting the MCP server.
- If you operate private wikis, populate the config with your wiki details, including token or username/password as needed.
- For authenticated tools (🔐), have OAuth2 tokens configured in your wiki per the provided authentication guide.
Additional notes
Environment variables and configuration tips:
- CONFIG: Path to your configuration file (config.json). Required when interacting with private wikis or when you need specific wiki mappings.
- MCP_TRANSPORT: Type of MCP transport (stdio or http). Default is stdio if not specified.
- PORT: Port for HTTP transport if using MCP over HTTP (default 3000). Common issues:
- If a tool requires authentication, ensure your wiki has OAuth2 enabled and that the token/credentials are correctly set in config.json.
- After add-wiki or remove-wiki operations, clients should refresh resources via notifications/resources/list_changed as described in the docs.
- Use the provided example config.json structure as a starting point to avoid missing required fields.
Related MCP Servers
mcp-agent
Build effective agents using Model Context Protocol and simple workflow patterns
git
An MCP (Model Context Protocol) server enabling LLMs and AI agents to interact with Git repositories. Provides tools for comprehensive Git operations including clone, commit, branch, diff, log, status, push, pull, merge, rebase, worktree, tag management, and more, via the MCP standard. STDIO & HTTP.
pluggedin-app
The Crossroads for AI Data Exchanges. A unified, self-hostable web interface for discovering, configuring, and managing Model Context Protocol (MCP) servers—bringing together AI tools, workspaces, prompts, and logs from multiple MCP sources (Claude, Cursor, etc.) under one roof.
filesystem
A Model Context Protocol (MCP) server for platform-agnostic file capabilities, including advanced search/replace and directory tree traversal
mindbridge
MindBridge is an AI orchestration MCP server that lets any app talk to any LLM — OpenAI, Anthropic, DeepSeek, Ollama, and more — through a single unified API. Route queries, compare models, get second opinions, and build smarter multi-LLM workflows.
symfony
A Symfony package designed for building secure servers based on the Model Context Protocol, utilizing Server-Sent Events (SSE) and/or StreamableHTTP for real-time communication. It offers a scalable tool system tailored for enterprise-grade applications.