HowToCook-MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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_getAllRecipesC | 获取所有菜谱 |
| mcp_howtocook_getRecipesByCategoryC | 根据分类查询菜谱，可选分类有: |
| mcp_howtocook_recommendMealsC | 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_whatToEatB | 不知道吃什么？根据人数直接推荐适合的菜品组合 |
| mcp_howtocook_getRecipeByIdB | 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
Most tools have distinct purposes: getAllRecipes, getRecipeById, and getRecipesByCategory handle recipe retrieval in different ways, while recommendMeals and whatToEat focus on recommendation. However, recommendMeals and whatToEat could be confused as both recommend dishes based on similar inputs like number of people, though recommendMeals adds dietary restrictions and meal planning.
All tool names follow a consistent snake_case pattern with the prefix 'mcp_howtocook_' and descriptive verb_noun combinations (e.g., getAllRecipes, getRecipeById). This uniformity makes the tools predictable and easy to understand.
With 5 tools, this server is well-scoped for a cooking/recipe domain. It covers core operations like retrieval, filtering, and recommendation without being overwhelming or too sparse, fitting typical server sizes of 3-15 tools.
The tool set covers read and recommendation operations well but lacks create, update, or delete tools for recipes, which are common in recipe management. This gap could limit agents from performing full lifecycle tasks, though retrieval and recommendation are adequately handled.