
What's Cooking MCP server
Which MCP servers are What's Cooking's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.
read 2026-10-24
- Registry nameguide.whatscooking/whats-cookingverified in the MCP registry
The registry name sits under whatscooking.guide. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-10-24
- Tools3
- Server calls itselfwhats-cooking
- Server version1.0.0
- Protocol version2025-06-18
On 2026-10-24 the server answered initialize and tools/list without a sign-in. First answer in 439 ms.
- Whether its tools do the product's job has not been judged yet.
- Checked on 3 of the 7 days it takes to judge reliability.
Once connected
- For "Pick one recipe from whatever ingredients are on hand", the likely first call is whats_for_dinner.
Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.
- INITE MCP scoreafter a weeka score needs 7 daily checks: 3 so far
- Answeredmeasuring3 of the 7 daily checks it takes to print a share
- Median first answer571 ms
- Space in an agent's context≈ 637 tokensthe definitions of all its tools (3), which an agent carries on every turn
- Tool definitionsA · 100 of 100
- Typed results0 of 3 toolsdeclared outputSchema: results come typed, read once
- Every tool passes all six checks.
What an agent can do with it
- can do · Pick one recipe from whatever ingredients are on hand
- not sure · Build a dinner party menu with co-hosts
- not sure · Plan a rolling weekly meal plan with a shared grocery list
Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?
Worth a look
None of the five warning signs in these definitions.
A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →
whats_for_dinnerWhat should I cook tonight with what I have? Gusto, What's Cooking's chef, decides one complete dinner and returns the full recipe, steps, and a list of what to buy. Inputs (all optional): have (what is already in the kitchen, a list or a…
browse_exploreWhat recipes have people and Gusto shared on What's Cooking? Inputs (all optional): query (matched against titles, tags and ingredients), author (e.g. "Gusto"), limit (default 5, max 20). Returns short picks; call get_explore_recipe with…
get_explore_recipeWhat's the full recipe for this Explore pick? Inputs: id (from browse_explore, required), servings (optional; quantities are scaled when it differs from the original). Example: {"id":"<id from browse_explore>","servings":4}
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"whats-cooking": {
"type": "http",
"url": "https://whatscooking.guide/mcp-server"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http whatscooking https://whatscooking.guide/mcp-serverclaude.ai, ChatGPT and other clients: add https://whatscooking.guide/mcp-server as a custom connector in the settings.
OpenAPI spec
2 paths, read 2026-10-24. Open the spec ↗
Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.
Cookies
Before we count this visit
Analytics and ad measurement tell us which pages and which of our ads do their job: Google Analytics and Google Ads, the Meta pixel, Yandex Metrica, and one first-party id of our own. Nothing is stored until you answer, and declining changes nothing about the site.