spoonacular-mcp
Enables AI assistants to search for recipes, get nutritional information, find ingredients, and more through the Spoonacular Food API using natural language.
README
Spoonacular MCP Server
A Model Context Protocol (MCP) server that provides access to the Spoonacular Food API. This server enables AI assistants to search for recipes, get nutritional information, find ingredients, and more through the MCP protocol.
Features
- Recipe Search: Search for recipes by ingredients, diet, cuisine, and other criteria
- Recipe Information: Get detailed recipe information including ingredients, instructions, and nutrition
- Ingredient Search: Find and explore ingredient information
- Nutrition Analysis: Analyze nutrition for ingredient lists
- Recipe by Ingredients: Find recipes based on available ingredients
- Random Recipes: Get random recipe suggestions with optional filtering
Quick Start
Installation
npm install -g spoonacular-mcp
Setup
-
Get a Spoonacular API key (free at https://spoonacular.com/food-api/console#Dashboard)
-
Set your API key as an environment variable:
# Windows (PowerShell) $env:SPOONACULAR_API_KEY="your_api_key_here" # macOS/Linux export SPOONACULAR_API_KEY="your_api_key_here"
Usage with MCP Clients
Add this configuration to your MCP client (Claude Desktop, etc.):
{
"servers": {
"spoonacular": {
"command": "spoonacular-mcp",
"env": {
"SPOONACULAR_API_KEY": "your_api_key_here"
}
}
}
}
Test the Installation
# Set your API key
export SPOONACULAR_API_KEY="your_key_here"
# Test the server
echo '{"jsonrpc":"2.0","id":1,"method":"tools/list","params":{}}' | spoonacular-mcp
Available Tools
search_recipes
Search for recipes with various filters.
Parameters:
query(string): Search query for recipesnumber(number, 1-100): Number of results (default: 10)diet(string, optional): Diet type (vegetarian, vegan, gluten-free, etc.)intolerances(string, optional): Comma-separated intolerancesincludeIngredients(string, optional): Required ingredients (comma-separated)excludeIngredients(string, optional): Ingredients to exclude (comma-separated)type(string, optional): Meal type (main course, side dish, dessert, etc.)cuisine(string, optional): Cuisine type (italian, mexican, chinese, etc.)
get_recipe_information
Get detailed information about a specific recipe.
Parameters:
id(number): Recipe IDincludeNutrition(boolean): Include nutrition information (default: false)
search_ingredients
Search for ingredients by name.
Parameters:
query(string): Ingredient search querynumber(number, 1-100): Number of results (default: 10)metaInformation(boolean): Include meta information (default: false)
analyze_nutrition
Analyze nutrition for a list of ingredients.
Parameters:
ingredientList(string): List of ingredients, one per lineservings(number): Number of servings
find_recipes_by_ingredients
Find recipes based on available ingredients.
Parameters:
ingredients(string): Comma-separated list of available ingredientsnumber(number, 1-100): Number of recipes (default: 5)ranking(number, 1-2): Ranking strategy (1=maximize used, 2=minimize missing)
get_random_recipes
Get random recipes with optional filtering.
Parameters:
number(number, 1-100): Number of random recipes (default: 1)tags(string, optional): Comma-separated tags for filtering
Development
To run in development mode:
npm run dev
To build:
npm run build
API Rate Limits
The free Spoonacular API plan includes:
- 150 requests per day
- Rate limiting applies
Consider upgrading to a paid plan for production use.
License
ISC
Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。