
Wraps JokeAPI v2 to let Claude search jokes by keyword and list available categories like programming, general, or knock-knock. You get two tools: search_jokes returns matching jokes with their type and content flags, while get_joke_categories shows what filters you can apply. It's hosted on Pipeworx's gateway, so no local setup or API keys needed. Mostly useful for demos, testing conversational flows, or adding levity to chatbots. The API is free and public, so you can just drop the URL into your MCP config and start pulling jokes immediately.
Jokes MCP — wraps JokeAPI v2 (free, no auth)
Part of Pipeworx — an MCP gateway connecting AI agents to 1476+ live data sources.
| Tool | Description |
|---|---|
get_joke | Get a random joke, optionally filtered by category (e.g., 'general', 'programming') or type ('single' or 'twopart'). Returns joke text, category, and content flags. |
search_jokes | Search jokes by keyword or phrase. Returns matching jokes with categories, types, and content flags. |
get_joke_categories | List all available JokeAPI joke categories (e.g., Programming, Misc, Dark, Pun, Spooky, Christmas). Use the returned category names as the category input to get_joke or search_jokes. |
get_joke_flags | List all content filter flags (e.g., explicit, political, racist). Use to understand what filters exclude. |
Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):
{
"mcpServers": {
"jokes": {
"url": "https://gateway.pipeworx.io/jokes/mcp"
}
}
}
tools/list at https://gateway.pipeworx.io/jokes/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 Jokes data" })
The gateway picks the right tool and fills the arguments automatically.
MIT