How to Use the Spoonacular MCP in OpenAI Agents SDK

Q: Can the OpenAI Agents SDK handle complex recipe planning with Spoonacular Alternative?

Yep. You can combine tools like recipesbyingredients and analyzerecipe. The agent figures out the steps: check ingredients, then analyze the best match for dietary needs.

Q: Does the MCP Server support importing recipes?

Yeah. You can use the extractrecipe tool to pull recipe data directly from a URL. It's cleaner than manual entry.

Q: If I use Spoonacular Alternative with OpenAI Agents SDK, how do I get detailed instructions?

Use getrecipeinstructions. This function provides step-by-step analysis for a recipe ID you pass in. It's designed to give clear, executable steps.

Build autonomous recipe agents using the OpenAI Agents SDK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Spoonacular MCP to OpenAI Agents SDK

Create your Vinkius account to connect Spoonacular to OpenAI Agents SDK — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Spoonacular with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Analyze recipes with the MCP Server.

Use `analyze_recipe` to run a detailed data enrichment process on any given recipe. This tool goes beyond simple ingredients, pulling in deep contextual data that helps your agent make better decisions about food suggestions. It's also useful for calling `get_recipe_nutrition`, which provides specific metrics like calories and fat counts so your agents can filter out meals based on strict dietary requirements.

Find recipes by ingredients.

`recipes_by_ingredients` solves the 'what should I cook?' problem when you're staring at a full fridge. You pass in what you have, and it ranks recipes based on ingredient match count. If you need more general ideas, `random_recipes` gives suggestions. You can even layer in dietary tags to narrow down those random hits.

Process multiple recipe data points.

`get_recipes_bulk` lets your agent grab information for many recipes at once instead of making dozens of individual calls. This saves time and makes the overall workflow much faster. You can also use `search_grocery_products` to check inventory before planning, letting your system verify if a recipe's ingredients are actually available locally.

Setup guide

Set up Spoonacular MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Spoonacular tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Spoonacular tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Spoonacular tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Spoonacular Agent",
            instructions="You have access to Spoonacular tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Spoonacular. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Spoonacular now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Spoonacular MCP in OpenAI Agents SDK

The agent auto-discovers the MCP Server tools; you just pass the endpoint URL. Your agents can then call functions like `search_recipes` to pull basic recipe metadata instantly.

This server handles structured food and nutritional data, specifically ingredient lists, nutrient profiles (`get_recipe_nutrition`), and recipes found via `search_recipes`.

Yep. You can combine tools like `recipes_by_ingredients` and `analyze_recipe`. The agent figures out the steps: check ingredients, then analyze the best match for dietary needs.

Yeah. You can use the `extract_recipe` tool to pull recipe data directly from a URL. It's cleaner than manual entry.

Use `get_recipe_instructions`. This function provides step-by-step analysis for a recipe ID you pass in. It's designed to give clear, executable steps.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript