
This is a free, no-auth gateway to the Cat as a Service API for dropping cat images into your AI workflows. It's part of Pipeworx, which wraps 250+ data sources behind streamable HTTP endpoints so you don't need to configure local transport layers. You can either call the CATAAS tools directly or use the ask_pipeworx natural language interface to let the gateway pick the right endpoint and arguments. Useful when you need quick placeholder images for testing UI flows or just want to add cats to literally anything. The source doesn't list specific tools, but it's a straightforward HTTP MCP that works with Claude Desktop, Cursor, and Windsurf out of the box.
CATAAS MCP — Cat as a Service (free, no auth)
Part of Pipeworx — an MCP gateway connecting AI agents to 1476+ live data sources.
| Tool | Description |
|---|---|
random_cat | Get a random cat image. Returns image URL, cat ID, and associated tags. |
cat_by_tag | Get a random cat image matching a specific tag (e.g., 'orange', 'cute', 'sleepy'). Returns image URL, cat ID, and tags. |
list_tags | List all available cat tags for filtering. Use tag names with cat_by_tag to find cats by appearance or behavior. |
Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):
{
"mcpServers": {
"cataas": {
"url": "https://gateway.pipeworx.io/cataas/mcp"
}
}
}
tools/list at https://gateway.pipeworx.io/cataas/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 Cataas data" })
The gateway picks the right tool and fills the arguments automatically.
MIT