How-To-Cook
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| XBY_APIKEY | Yes | 你的实际apikey (Your actual API key) |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| mcp_howtocook_getAllRecipesD | 获取所有菜谱 |
| mcp_howtocook_getRecipesByCategoryC | 根据分类查询菜谱，可选分类有: 水产, 早餐, 调料, 甜品, 饮品, 荤菜, 半成品加工, 汤, 主食, 素菜 |
| mcp_howtocook_recommendMealsB | 根据用户的忌口、过敏原、人数智能推荐菜谱，创建一周的膳食计划以及大致的购物清单 |
| mcp_howtocook_whatToEatC | 不知道吃什么？根据人数直接推荐适合的菜品组合 |
| mcp_howtocook_getRecipeByIdC | 根据菜谱名称或ID查询指定菜谱的完整详情，包括食材、步骤等 |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 5 tools
Each tool has a clearly distinct purpose: getAllRecipes retrieves all recipes, getRecipeById fetches a specific recipe by ID/name, getRecipesByCategory filters by category, recommendMeals creates personalized meal plans, and whatToEeat offers quick dish recommendations. There is no overlap or ambiguity in their functions.
All tool names follow a consistent verb_noun pattern with the prefix 'mcp_howtocook_' and use camelCase (e.g., getAllRecipes, getRecipeById). The naming is uniform and predictable across all tools.
With 5 tools, the server is well-scoped for a cooking/recipe domain. Each tool serves a distinct and essential function, from basic retrieval to advanced planning, making the count appropriate and efficient.
The toolset covers core operations like retrieval, filtering, and recommendation, but lacks CRUD capabilities for creating, updating, or deleting recipes. This is a minor gap, as agents can still perform most common tasks, but full lifecycle management is not supported.