Wikimedia Image Search
Wikimedia Image Search MCP Server
This MCP (Model Context Protocol) server enables AI assistants to search for images on Wikimedia Commons. It provides detailed metadata and optional thumbnail composites to help AI models visually compare results.
Overview
This server is designed to give AI assistants "eyes" when searching for visual content. Instead of guessing based on filenames or text descriptions alone, the AI can retrieve a structured list of image metadata and a composite image containing thumbnails of the search results.
This capability is particularly useful when an AI assistant needs to:
- Find suitable images for creating websites, articles, or presentations.
- Select images for educational materials or books.
- Verify the visual content of an image before recommending it.
- Compare multiple images to choose the most relevant one for a specific context.
By providing both metadata (license, author, description, dimensions) and a visual preview, the AI can make informed decisions about which images to use or download.
Note: This project is unofficial and is not affiliated with or endorsed by Wikimedia Commons or the Wikimedia Foundation. It uses their public API to provide image search functionality.
FAQ
Can it be used with any LLM?
Yes, it is designed to work with various LLMs and clients that support the Model Context Protocol (MCP), such as Claude Desktop, Cursor, VS Code and many others.
Do I need an API key?
No, this server interacts with the public Wikimedia Commons API. You do not need to configure a personal API key to use this tool.
How can I use the images found?
Usage depends on the license. The AI receives license metadata for every result and can be instructed to filter specifically for "no_restrictions" (CC0/Public Domain) content.
Server Config
{
"mcpServers": {
"wikimedia-image-search": {
"command": "npx",
"args": [
"-y",
"wikimedia-image-search-mcp"
]
}
}
}