Wikimedia Commons data API

3 endpoints for Wikimedia Commons: search, file, files. One API key, one JSON schema, as MCP tools or REST.

Endpoints

Call any of them over MCP with call_endpoint and its path, or over REST.

EndpointReturnsCreditsCache
searchGET /v1/wikimedia_commons/searchMedia files on Wikimedia Commons matching a keyword, with image URL, size, author and license.12 min
fileGET /v1/wikimedia_commons/fileOne Wikimedia Commons file: original and thumb url, size, mime, uploader, licence and categories.110 min
filesGET /v1/wikimedia_commons/filesFiles inside one Wikimedia Commons category, each with url, size, mime, uploader and licence.12 min

Connect your agent over MCP

Remote MCP server: https://data.openkrill.app/mcp with your key in the x-api-key header.

Claude Code · Run in a terminal
claude mcp add --transport http krilldata \
  https://data.openkrill.app/mcp \
  --header "x-api-key: YOUR_API_KEY"
Cursor · Add to ~/.cursor/mcp.json
{
  "mcpServers": {
    "krilldata": {
      "url": "https://data.openkrill.app/mcp",
      "headers": {
        "x-api-key": "YOUR_API_KEY"
      }
    }
  }
}
Claude Desktop · Add to claude_desktop_config.json
{
  "mcpServers": {
    "krilldata": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://data.openkrill.app/mcp",
        "--header",
        "x-api-key:${API_KEY}"
      ],
      "env": {
        "API_KEY": "YOUR_API_KEY"
      }
    }
  }
}
Wikimedia Commons data API for AI agents | KrillData