Wikimedia Image Search

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.

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.

- Node.js: Version 18 or higher.
- MCP Client: A compatible client such as VS Code, Cursor, Claude Code, Windsurf, Cline, Claude Desktop...

To use this server, configure your MCP client to run it usingnpx.

Add the following configuration to your MCP settings file (typically located at%APPDATA%\Code\User\globalStorage\mcp-servers.jsonon Windows or~/Library/Application Support/Code/User/globalStorage/mcp-servers.jsonon macOS).

{ "mcpServers": { "wikimedia-image-search": { "command": "npx", "args": [ "-y", "wikimedia-image-search-mcp" ] } } }

Go toCursor Settings>MCP>Add new MCP Server.

- Name: wikimedia-image-search
- Type: command
- Command:npx -y wikimedia-image-search-mcp

Alternatively, edit your.cursor/mcp.jsonfile:

{ "mcpServers": { "wikimedia-image-search": { "command": "npx", "args": [ "-y", "wikimedia-image-search-mcp" ] } } }

Edit yourclaude_desktop_config.jsonfile (typically located at%APPDATA%\Claude\claude_desktop_config.jsonon Windows or~/Library/Application Support/Claude/claude_desktop_config.jsonon macOS).

{ "mcpServers": { "wikimedia-image-search": { "command": "npx", "args": [ "-y", "wikimedia-image-search-mcp" ] } } }

Run the following command in your terminal:

claude mcp add wikimedia-image-search -- npx -y wikimedia-image-search-mcp

This server exposes a single tool:wikimedia_search_images.

The tool accepts the following parameters:

- query(string, required): The search terms (e.g., "sunset ocean", "eiffel tower").
- limit(number, optional): Maximum number of results to return (default: 9, max: 50).
- offset(number, optional): Number of results to skip for pagination.
- license(string, optional): Filter by license. Options:"all"(default) or"no_restrictions"(CC0/Public Domain).
- include_thumbnails(boolean, optional): Whether to generate and return a composite image of thumbnails (default:true).
- Fetching: The tool queries the Wikimedia Commons API using the provided search terms and filters. It retrieves raw JSON data containing image URLs, metadata, and license information.
- Processing: The raw JSON response is parsed and transformed into a clean, structured list ofImageMetadataobjects.
- Formatting:

- Text: The metadata list is converted into a YAML-formatted string. This provides the AI with a readable, structured text overview of the results (including file size, dimensions, author, and license).
- Visual: Ifinclude_thumbnailsis true, the tool downloads the thumbnail for each result. It then uses thesharplibrary to composite these thumbnails into a single grid image, with index numbers overlaid on each image.

You can view examples of the output files in thetest-output/directory:

- wikimediaSearchResults.json: The raw JSON response from the Wikimedia API.
- formattedSearchResults.txt: The YAML-formatted text response.
- thumbnailComposite.jpeg: The generated visual grid of search results.

git clone https://github.com/yanexr/wikimedia-image-search-mcp.git cd wikimedia-image-search-mcp

{ "mcpServers": { "wikimedia-local": { "command": "node", "args": [ "C:/path/to/wikimedia-image-search-mcp/dist/index.js" ] } } }

Testing and Debugging: You can use the MCP Inspector to test the server interactively:

Search global news using natural language. Webz.io News Search API returns the most relevant articles and content, with filters for source, country, language, date, sentiment, and category.

Fetch, convert, and search AWS documentation pages, with recommendations for related content.

Search campgrounds around the world on campertunity, check availability, and provide booking links.

The Ferryhopper MCP Server exposes ferry routes, schedules and booking redirects so an AI assistant can discover connections across Europe and the Mediterranean and send users to Ferryhopper to complete bookings.

All-in-One SEO & Web Intelligence Toolkit API from FetchSERP.

MCP server that provides read-only access to HyperKitty, the web-based email archive component of Mailman 3.

At Sunrise Apps, we believe AI agents should be limitless, especially when it comes to visual data. We created ImageSorcery to bridge the critical gap in AI's ability to interact with and manipulate images directly, all while upholding the highest standards of privacy and security.

Just Domain is the domain registrar for businesses built with AI. Its remote MCP server checks availability and returns first-year and renewal pricing, plus a link to register on justdomain.ai, with DNS and WHOIS privacy in the same place. No account, no API key, read only. Endpoint: https://mcp.justdomain.ai/

Research tools, including a Sqlite-backed document stash

Semantic search over 9 free-license stock photo sources. Hosted remote server with OAuth — no API key to paste.

SerpApi MCP Server for Google and other search engine results