Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@cook-tool get the recipe for kung pao chicken"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
一个支持通过命令行查询菜谱和报菜名的菜谱查询工具，适用于烹饪爱好者和开发者。 A recipe query tool that supports querying recipes and reporting dish names through the command line, suitable for cooking enthusiasts and developers.## 工具列表 Tool List
本MCP服务封装下列工具，可让模型通过标准化接口调用以下功能。 本MCP服务封装下列工具，可让模型通过标准化接口调用以下功能。
工具 Tool | 描述 Description |
get_all_dishes | 获取所有可用菜品的名称列表 (菜单)。 |
get_dish_content | 根据提供的菜品名称获取其详细内容。 |
工具在线测试： https://mcp.xiaobenyang.com/inspector/1777316659522563
Online Tool test https://mcp.xiaobenyang.com/inspector/1777316659522563
Related MCP server: Recettes MCP Server
如何获取 XBY-APIKEY ？ How to get XBY-APIKEY ?
访问小笨羊科技网站 https://xiaobenyang.com，注册用户即可获得APIKEY Visit XiaoBenYang website https://xiaobenyang.com, register and get the APIKEY.
{
"mcpServers": {
"菜谱查询工具": {
"headers": {
"XBY-APIKEY": "<YOUR_XBY_APIKEY>"
},
"type": "sse",
"url": "https://mcp.xiaobenyang.com/1777316659522563/sse"
}
}
}{
"mcpServers": {
"菜谱查询工具": {
"headers": {
"XBY-APIKEY": "<YOUR_XBY_APIKEY>"
},
"type": "streamable_http",
"url": "https://mcp.xiaobenyang.com/1777316659522563/mcp"
}
}
}{
"mcpServers": {
"菜谱查询工具": {
"command": "npx",
"args": [
"-y",
"xiaobenyang-mcp"
],
"env": {
"XBY_APIKEY": "<YOUR_XBY_APIKEY>",
"mcpId": "1777316659522563",
},
"transport": "stdio"
}
}
}
获取所有可用菜品的名称列表 (菜单)。
Inputs: no named parameters.
根据提供的菜品名称获取其详细内容。
Inputs: dishName (required).
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 2 tools
The two tools have clearly distinct purposes: get_all_dishes retrieves a list of dish names (menu), while get_dish_content fetches detailed content for a specific dish based on its name. There is no overlap or ambiguity between these operations.
Both tools follow a consistent verb_noun pattern with 'get_' prefix and snake_case naming (get_all_dishes, get_dish_content). The naming is predictable and readable throughout.
With only 2 tools, the server feels thin for a cooking/recipe domain. It lacks essential operations like creating, updating, or deleting dishes, which limits its utility and scope. A minimal CRUD set would typically have at least 3-4 tools.
The tool surface is severely incomplete for a cooking domain. It only provides read operations (get all and get details), missing create, update, delete, search, or other lifecycle management tools. This will likely cause agent failures when trying to perform full workflows.
Recipe search, ingredient matching, nutrition filters and a private cookbook for any AI agent.
Search structured recipes, scale servings, match pantry ingredients, and build shopping lists.
Your personal recipe kitchen: save, fork, and cook recipes, build cookbooks, and shopping lists.
Search, save, organize, cook, and share recipes with any AI assistant.
