
Connects Claude to Openverse's Creative Commons media library through six focused tools: search and retrieve images or audio, plus discover related content by ID. Useful when you need properly licensed media for projects and want to browse, filter, and pull metadata without leaving your AI workflow. Part of the larger Pipeworx gateway, so you can add it standalone or get it bundled with 600+ other data sources. Supports plain English queries through ask_pipeworx if you'd rather describe what you want than call tools directly. Built on streamable HTTP, so no local processes to manage.
Openverse MCP — search the union catalog of Creative-Commons-licensed images + audio (Wikimedia, Flickr, museums, etc). Keyless (anonymous tier is rate-limited but usable).
Part of Pipeworx — an MCP gateway connecting AI agents to 1476+ live data sources.
search_images(query, filters?) — search CC-licensed imagessearch_audio(query, filters?) — search CC-licensed audioget_image(id) — single image recordget_audio(id) — single audio recordimage_related(id) — related imagesaudio_related(id) — related audiohttps://api.openverse.engineering/v1/
Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):
{
"mcpServers": {
"openverse": {
"url": "https://gateway.pipeworx.io/openverse/mcp"
}
}
}
tools/list at https://gateway.pipeworx.io/openverse/mcp returns the tools in the table
above plus the shared Pipeworx meta-tools — ask_pipeworx,
discover_tools, search_within, remember/recall and the rest of the
gateway-wide set. So the tool count you see is larger than this table: a
single-pack endpoint currently lists roughly 30 shared tools alongside the
pack's own. The connection's initialize response states its exact scope, and
is the authoritative answer for a given day.
This is deliberate, not multiplexing by accident. The meta-tools are what let a
scoped connection answer a question this pack does not cover — via
ask_pipeworx, which routes across the whole catalog — without you adding a
second MCP server. There is currently no way to mount a pack endpoint without
them; if the extra schemas cost you more context than the routing is worth,
connect to the full gateway once rather than to several pack endpoints.
Or connect to the full Pipeworx gateway to get every pack's tools listed directly, instead of just this one's:
{
"mcpServers": {
"pipeworx": {
"url": "https://gateway.pipeworx.io/mcp"
}
}
}
Both URLs reach the same gateway and the same 1476+ data sources. The
only difference is which pack's tools are listed directly; ask_pipeworx
reaches all of them from either one.
Instead of calling tools directly, you can ask questions in plain English — this works on the pack endpoint above as well as on the full gateway:
ask_pipeworx({ question: "your question about Openverse data" })
The gateway picks the right tool and fills the arguments automatically.
MIT