wikipedia -image-crawler

This MCP server provides two tools for working with images on Wikipedia Commons: wiki_image_search and wiki_image_info. The wiki_image_search tool lets you search for images by a text query and customize the number of results (1-50). It returns image URLs, dimensions, MIME types, and sizes, which you can then feed into your workflows or UIs. The wiki_image_info tool accepts a specific image title (for example, the exact File: name) and fetches detailed metadata including license information, author data, and full-resolution URLs along with description links. These tools are designed to help you locate public-domain or freely licensed images with proper attribution from Wikimedia Commons and retrieve rich metadata for attribution and licensing purposes.

Prerequisites:

• Node.js 18 or higher
• npm or pnpm installed

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

Usage integration (optional):

• To run locally after building: node build/index.js
• Integrate with Claude or other MCP clients by configuring the MCP server entry (see mcp_config) and pointing the client at the built index.js file.

Tips and notes:

• The server exposes two MCP tools: wiki_image_search and wiki_image_info. Use them via MCP-compatible payloads as shown in the Usage examples.
• Ensure you build the project before attempting to run the server (pnpm run build).
• When integrating with Claude Desktop or VSCode, you’ll typically use an absolute path to the built index.js file in your configuration.
• If you encounter permission or network issues, verify that your environment allows outgoing HTTP requests to Wikimedia Commons and that any proxies are configured correctly.
• If you plan to run multiple MCP servers, keep each server name unique in your mcp configuration to avoid conflicts.