Price Per TokenPrice Per Token
MediaWiki

MediaWiki

by professionalwiki

GitHub 60 1,477 uses Remote
0

About

MediaWiki MCP Server connects LLM clients to any MediaWiki-powered wiki (including Wikipedia, Fandom, and private instances) for comprehensive content management. Key capabilities: - Create, edit, move, and delete wiki pages with proper permission handling - Search page titles and content, including prefix-based searches - Retrieve page history, revisions, and file metadata - Upload files from local disk or URLs - Manage multiple wikis as MCP resources with dynamic addition/removal - Secure OAuth 2.0 authentication for authorized operations - Browse category members and access file objects - Support for restoring deleted pages

README

MediaWiki MCP Server

[](https://www.npmjs.com/package/@professional-wiki/mediawiki-mcp-server) [](https://smithery.ai/server/@ProfessionalWiki/mediawiki-mcp-server) [](./LICENSE)

An MCP (Model Context Protocol) server that enables Large Language Model (LLM) clients to interact with any MediaWiki wiki.

Feature

Tools

| Name | Description | Permissions | |---|---|---| | add-wiki | Adds a new wiki as an MCP resource from a URL. | - | | create-page 🔐 | Create a new wiki page. | Create, edit, and move pages | | delete-page 🔐 | Delete a wiki page. | Delete pages, revisions, and log entries | | get-category-members | Gets all members in the category | - | | get-file | Returns the standard file object for a file page. | - | | get-page | Returns the standard page object for a wiki page. | - | | get-page-history | Returns information about the latest revisions to a wiki page. | - | | get-revision | Returns the standard revision object for a page. | - | | remove-wiki | Removes a wiki resource. | - | | search-page | Search wiki page titles and contents for the provided search terms. | - | | search-page-by-prefix | Perform a prefix search for page titles. | - | | set-wiki | Sets the wiki resource to use for the current session. | - | | undelete-page 🔐 | Undelete a wiki page. | Delete pages, revisions, and log entries | | update-page 🔐 | Update an existing wiki page. | Edit existing pages | | upload-file 🔐 | Uploads a file to the wiki from the local disk. | Upload new files | | upload-file-from-url 🔐 | Uploads a file to the wiki from a web URL. | Upload, replace, and move files |

Resources

mcp://wikis/{wikiKey}

  • Credentials (e.g., token, username, password) are never exposed in resource content.
  • After add-wiki/remove-wiki, the server sends notifications/resources/list_changed so clients refresh.
  • Example list result

    {
      "resources": [
        {
          "uri": "mcp://wikis/en.wikipedia.org",
          "name": "wikis/en.wikipedia.org",
          "title": "Wikipedia",
          "description": "Wiki \"Wikipedia\" hosted at https://en.wikipedia.org"
        }
      ]
    }
    

    Example read result

    {
      "contents": [
        {
          "uri": "mcp://wikis/en.wikipedia.org",
          "mimeType": "application/json",
          "text": "{ \"sitename\":\"Wikipedia\",\"server\":\"https://en.wikipedia.org\",\"articlepath\":\"/wiki\",\"scriptpath\":\"/w\",\"private\":false }"
        }
      ]
    }
    

    Environment variables

    | Name | Description | Default | |---|---|---| | CONFIG | Path to your configuration file | config.json | | MCP_TRANSPORT | Type of MCP server transport (stdio or http) | stdio | | PORT | Port used for StreamableHTTP transport | 3000 |

    Configuration

    > Note: Config is only required when interacting with a private wiki or using authenticated tools.

    Create a config.json file to configure wiki connections. Use the config.example.json as a starting point.

    Basic structure

    {
      "defaultWiki": "en.wikipedia.org",
      "wikis": {
        "en.wikipedia.org": {
          "sitename": "Wikipedia",
          "server": "https://en.wikipedia.org",
          "articlepath": "/wiki",
          "scriptpath": "/w",
          "token": null,
          "username": null,
          "password": null,
          "private": false
        }
      }
    }
    

    Configuration fields

    | Field | Description | |---|---| | defaultWiki | The default wiki identifier to use (matches a key in wikis) | | wikis | Object containing wiki configurations, keyed by domain/identifier |

    Wiki configuration fields

    | Field | Required | Description | |---|---|---| | sitename | Yes | Display name for the wiki | | server | Yes | Base URL of the wiki (e.g., https://en.wikipedia.org) | | articlepath | Yes | Path pattern for articles (typically /wiki) | | scriptpath | Yes | Path to MediaWiki scripts (typically /w) | | token | No | OAuth2 access token for authenticated operations (preferred) | | username | No | Bot username (fallback when OAuth2 is not available) | | password | No | Bot password (fallback when OAuth2 is not available) | | private | No | Whether the wiki requires authentication to read (default: false) |

    Authentication setup

    For tools marked with 🔐, authentication is required.

    Preferred method: OAuth2 Token

    1. Navigate to Special:OAuthConsumerRegistration/propose/oauth2 on your wiki 2. Select "This consumer is for use only by [YourUsername]" 3. Grant the necessary permissions 4. After approval, you'll receive: - Client ID - Client Secret - Access Token 5. Add the token to your wiki configuration in config.json

    > *

    Related MCP Servers

    AI Research Assistant

    AI Research Assistant

    hamid-vakilzadeh

    AI Research Assistant provides comprehensive access to millions of academic papers through the Semantic Scholar and arXiv databases. This MCP server enables AI coding assistants to perform intelligent literature searches, citation network analysis, and paper content extraction without requiring an API key. Key features include: - Advanced paper search with multi-filter support by year ranges, citation thresholds, field of study, and publication type - Title matching with confidence scoring for finding specific papers - Batch operations supporting up to 500 papers per request - Citation analysis and network exploration for understanding research relationships - Full-text PDF extraction from arXiv and Wiley open-access content (Wiley TDM token required for institutional access) - Rate limits of 100 requests per 5 minutes with options to request higher limits through Semantic Scholar

    Web & Search
    12 8
    Linkup

    Linkup

    LinkupPlatform

    Linkup is a real-time web search and content extraction service that enables AI assistants to search the web and retrieve information from trusted sources. It provides source-backed answers with citations, making it ideal for fact-checking, news gathering, and research tasks. Key features of Linkup: - Real-time web search using natural language queries to find current information, news, and data - Page fetching to extract and read content from any webpage URL - Search depth modes: Standard for direct-answer queries and Deep for complex research across multiple sources - Source-backed results with citations and context from relevant, trustworthy websites - JavaScript rendering support for accessing dynamic content on JavaScript-heavy pages

    Web & Search
    2 24
    Math-MCP

    Math-MCP

    EthanHenrickson

    Math-MCP is a computation server that enables Large Language Models (LLMs) to perform accurate numerical calculations through the Model Context Protocol. It provides precise mathematical operations via a simple API to overcome LLM limitations in arithmetic and statistical reasoning. Key features of Math-MCP: - Basic arithmetic operations: addition, subtraction, multiplication, division, modulo, and bulk summation - Statistical analysis functions: mean, median, mode, minimum, and maximum calculations - Rounding utilities: floor, ceiling, and nearest integer rounding - Trigonometric functions: sine, cosine, tangent, and their inverses with degrees and radians conversion support

    Developer Tools
    22 81