recipe-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| COOKWITH_API_URL | No | API endpoint for the recipe service | https://cookwith.co |
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
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| generate_recipeA | Generate a new recipe based on natural language instructions and dietary preferences |
| transform_recipeB | Transform an existing recipe based on instructions (e.g., make it vegan, adjust calories, change servings) |
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 2 tools
generate_recipe creates a new recipe, while transform_recipe modifies an existing one. The semantic boundary is clear, with no overlap in purpose.
Both tools follow a consistent verb_noun pattern: generate_recipe and transform_recipe. The verbs are distinct and the object is uniform.
With only two tools, the server feels thin for a recipe domain. While the scope could be narrowly focused on generation, the count is borderline.
transform_recipe requires an existing recipe, but there is no tool to retrieve or list recipes. This is a significant gap that leaves agents unable to obtain the input needed for transformation.