Connects your MCP client directly to Wikimedia Commons through the MediaWiki Action API. You get five core tools: full-text search across the entire Commons library, file metadata retrieval with license and thumbnail URLs, revision history lookups, category browsing, and a random image generator that can filter by category. Runs as a streamable HTTP server through the Pipeworx gateway, which also offers an ask_pipeworx tool that translates plain English questions into the appropriate API calls. Useful when you need programmatic access to Commons media files without writing your own MediaWiki API wrapper, or when building agents that work with openly licensed images, audio, and video.
Wikimedia Commons MCP — Action API for files.
Part of Pipeworx — an MCP gateway connecting AI agents to 673+ live data sources.
| Tool | Description |
|---|---|
search | Full-text search across Commons. |
file_info | File metadata (size, mime, license, upload date, thumbnail urls). |
file_revisions | File revision history. |
category_members | Items in a Commons category. |
random_image | Random image (optionally from a category). |
Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):
{
"mcpServers": {
"commons-wikimedia": {
"url": "https://gateway.pipeworx.io/commons-wikimedia/mcp"
}
}
}
Or connect to the full Pipeworx gateway for access to all 673+ data sources:
{
"mcpServers": {
"pipeworx": {
"url": "https://gateway.pipeworx.io/mcp"
}
}
}
Instead of calling tools directly, you can ask questions in plain English:
ask_pipeworx({ question: "your question about Commons Wikimedia data" })
The gateway picks the right tool and fills the arguments automatically.
MIT
com.mcparmory/google-search
io.github.pipeworx-io/brave-search
marcopesani/mcp-server-serper
brave/brave-search-mcp-server
com.mcparmory/google-search-console
acamolese/google-search-console-mcp