
Wraps TheMealDB's free tier API to bring recipe data into your MCP client without any auth setup. You get four straightforward tools: search by meal name, fetch full recipe details by ID, pull a random recipe for inspiration, or find everything you can make with a specific ingredient. Each recipe includes ingredients with measurements and step-by-step instructions. Hosted on the Pipeworx gateway, which means you can either add just the recipes endpoint or connect to their full gateway for access to 600+ other data sources. Useful when you're building cooking assistants, meal planning features, or just want to let Claude help you figure out what to make for dinner.
Recipes MCP — wraps TheMealDB API (free tier, no auth)
Part of Pipeworx — an MCP gateway connecting AI agents to 1476+ live data sources.
| Tool | Description |
|---|---|
search_meals | Search TheMealDB for recipes by meal name. Returns full recipe details — category, cuisine area, ingredients with measurements, step-by-step instructions, tags, thumbnail, and YouTube/source URLs. |
get_meal | Get complete recipe details including ingredients with measurements and step-by-step cooking instructions. Pass a meal ID from search_meals or random_meal. |
random_meal | Get a random meal recipe with full ingredients and cooking instructions. Use when you need recipe inspiration without a specific search. |
meals_by_ingredient | Find all recipes using a specific ingredient (e.g., "chicken", "garlic", "pasta"). Returns meal names and IDs to pass to get_meal. |
Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):
{
"mcpServers": {
"recipes": {
"url": "https://gateway.pipeworx.io/recipes/mcp"
}
}
}
tools/list at https://gateway.pipeworx.io/recipes/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 Recipes data" })
The gateway picks the right tool and fills the arguments automatically.
MIT