Skip to main content
Glama
wikipedia-mcp-image-crawler

wikipedia-mcp-image-crawler

by dazeb

Wikipedia MCP Image Crawler

A Model Context Protocol (MCP) server for searching and retrieving images from Wikipedia Commons. This server provides tools to search for images and fetch detailed metadata through the Wikipedia API.

I created this tool because i needed images of Greek philosopher's. I needed to mak sure i had full attribution and licenses. This will search wikipedia only and download images that are in the public domain and free to use.

Features

Tools

  • wiki_image_search - Search for images on Wikipedia Commons

    • Search by query with customizable result limits (1-50)

    • Returns image URLs, dimensions, MIME types, and sizes

  • wiki_image_info - Get detailed information about specific images

    • Fetches comprehensive metadata including license and author

    • Returns full resolution URLs and description links

Related MCP server: Wikipedia MCP Server

Installation

Prerequisites

  • Node.js 18 or higher

  • npm or pnpm package manager

Local Installation

  1. Clone the repository:

    git clone https://github.com/dazeb/wikipedia-mcp-image-crawler.git
    cd wikipedia-mcp-image-crawler
  2. Install dependencies:

    pnpm install
  3. Build the server:

    pnpm run build

Integration with Claude

Claude Desktop App

Add the server configuration to your Claude config file:

MacOS:

nano ~/Library/Application\ Support/Claude/claude_desktop_config.json

Linux:

nano ~/.config/Claude/claude_desktop_config.json

Windows:

notepad %APPDATA%\Claude\claude_desktop_config.json

Add this configuration (adjust the path to where you cloned the repository):

{
  "mcpServers": {
    "wikipedia-mcp-server": {
      "command": "node",
      "args": ["/absolute/path/to/wikipedia-mcp-image-crawler/build/index.js"],
      "disabled": false,
      "autoApprove": []
    }
  }
}

VSCode Extensions

Cline VSCode Extension

For the Cline VSCode extension, add to:

MacOS:

~/Library/Application\ Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json

Linux:

~/.config/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json

Windows:

%APPDATA%\Code\User\globalStorage\saoudrizwan.claude-dev\settings\cline_mcp_settings.json

For VS Code Insiders, replace Code with Code - Insiders in the paths above.

Add this configuration to the JSON file:

{
  "mcpServers": {
    "wikipedia-mcp-server": {
      "command": "node",
      "args": ["/absolute/path/to/wikipedia-mcp-image-crawler/build/index.js"],
      "disabled": false,
      "autoApprove": []
    }
  }
}

If the file already contains other MCP servers, add this entry to the existing mcpServers object.

Usage

Once installed, the server provides two main tools:

Search for images matching a query:

{
  "name": "wiki_image_search",
  "arguments": {
    "query": "golden gate bridge",
    "limit": 5
  }
}

Image Information

Get detailed metadata for a specific image:

{
  "name": "wiki_image_info",
  "arguments": {
    "title": "File:Golden Gate Bridge.jpg"
  }
}

Development

Running in Watch Mode

For development with auto-rebuild:

pnpm run watch

Debugging

Since MCP servers communicate over stdio, use the MCP Inspector for debugging:

pnpm run inspector

This will provide a URL to access the debugging interface in your browser.

Available Tools

2 tools
wiki_image_infoB

Get detailed information about a specific Wikipedia image

Inputs: title (required).

Tool Schema Changelog

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

Loading tool schema changelog…

    TDQS

    B3.2/5.0

    Scored across 2 tools

    Disambiguation5/5

    The two tools serve clearly distinct purposes: one searches for images on Commons, the other retrieves details about a specific image. There is no ambiguity or overlap in their functionality.

    Naming Consistency5/5

    Both tool names follow the consistent pattern 'wiki_image_<verb>', using snake_case and a clear prefix. This makes the tool set easy to navigate and predict.

    Tool Count3/5

    With only two tools, the server feels minimal for something called an 'image crawler'. While the tools cover basic search and info retrieval, more operations (e.g., download, list) would better justify the name.

    Completeness2/5

    The tool set lacks critical operations for a crawler, such as downloading images or browsing categories. An agent would hit dead ends when trying to actually collect image data.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      B
      quality
      D
      maintenance
      This MCP server enables AI assistants to search for images on Wikimedia Commons, providing detailed metadata and optional thumbnail combinations to assist AI models in visual comparisons.
      1
      2
      Apache 2.0
    • A
      license
      A
      quality
      D
      maintenance
      Enables AI assistants to access Wikipedia content, search articles, retrieve historical events, and fetch images through the Wikipedia API.
      4
      13 npm
      1
      MIT