How to Use the Spoonacular MCP in AutoGen

Facilitate consensus decision making with AutoGen and our MCP Server.

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 AutoGen

Create your Vinkius account to connect Spoonacular to AutoGen — 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Debating Recipe Options with AutoGen

Set up multiple agents to debate the best meal plan. One agent can use `recipes_by_ingredients` (based on fridge contents) while a 'Nutrition Agent' simultaneously calls `get_recipe_nutrition`. They negotiate which recipe is optimal. The MCP Server facilitates this deliberation by providing conflicting, yet valid, data points that agents must reconcile.

Consensus-Driven Search for AutoGen

Instead of a single search, multiple agents can run different searches—one using `search_recipes` and another running `random_recipes`. They discuss the overlaps, flagging common criteria like 'low prep time' or 'Mexican cuisine.' This consensus approach prevents any single tool call from dictating the final answer.

Analyzing Multiple Sources with AutoGen

You can task one agent to use `extract_recipe` on a blog link, and another agent to use `analyze_recipe` on a raw ingredient list. The agents then debate which source provides the most reliable recipe data. This multi-source validation is where the MCP Server shines for complex decision architecture.

Setup guide

Set up Spoonacular MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Spoonacular tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Spoonacular_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Spoonacular data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Spoonacular_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Spoonacular data")
    print(result.messages[-1].content)

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 AutoGen

You pass the tools list to the AssistantAgent. Agents then use their internal logic to debate which tool—like `get_recipe_info` or `guess_dish_type`—is required at any given moment to advance the conversation.

The server provides structured ingredient lists, nutritional metrics, and recipe text. The `recipes_by_nutrients` tool is key for giving the 'Dietary Agent' hard facts to argue with.

Yes. Agents can collaborate: one agent finds recipes by ingredients, and another checks those results against nutritional guidelines using `get_recipe_nutrition`. They must agree on the final list.

AutoGen's strength is its debate mechanism. It forces agents to argue their conclusions based on the MCP Server data, ensuring the final output has been vetted by multiple perspectives.

The server touches ingredient names and nutritional metrics. When setting up agent conversations, make sure sensitive user data isn't passed as a required argument to the tool calls.

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