How to Use the Spoonacular MCP in Pydantic AI

Q: Can Pydantic AI handle complex recipe planning with Spoonacular Alternative?

Absolutely. You can chain tools like recipesbyingredients and then use getrecipeinfo. The validation layer ensures the data passed from one step to the next is always correct.

Q: Does the MCP Server support importing recipes?

Yes, via extractrecipe. Because of Pydantic's role, you know that even scraped blog content will be mapped into a predictable and reliable data structure.

Guarantee structured food data with Pydantic AI and the 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 Pydantic AI

Create your Vinkius account to connect Spoonacular to Pydantic AI — 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Validate recipe enrichment with the MCP Server.

Use `analyze_recipe` to get enriched, type-safe data points for any given recipe. Since every response is validated by Pydantic, you never have to worry about unexpected JSON fields corrupting your agent's state. Similarly, calling `get_recipe_nutrition` guarantees that the output structure always includes expected metrics like total calories and serving size.

Match ingredients for reliable data.

`recipes_by_ingredients` provides a structured list of matches based on user-provided inventory. If the API returns an unexpected format, Pydantic fails loudly with a validation error—you know instantly that the tool failed. You can also use `guess_dish_type` to classify unknown recipes, getting a guaranteed type output for your data models.

Search and gather recipe details.

`search_recipes` gives you basic metadata (title, ready time) in a predictable format. This is ideal for populating simple database tables. If you need deep context, `get_recipe_info` pulls all the necessary fields into a validated object. It's designed for maximum data integrity.

Setup guide

Set up Spoonacular MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "spoonacular-alternative-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Spoonacular tools.",
)

result = await agent.run("List recent Spoonacular transactions")
print(result.output)

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 Pydantic AI

It guarantees that every single piece of returned data, whether from `search_recipes` or `get_recipe_nutrition`, adheres to a strict Python type schema. You don't get silent corruption; you get explicit errors.

The toolset uses Pydantic models for validation at runtime. This means if the underlying MCP Server changes its output structure, your agent fails gracefully and tells you exactly what's wrong.

Absolutely. You can chain tools like `recipes_by_ingredients` and then use `get_recipe_info`. The validation layer ensures the data passed from one step to the next is always correct.

Yes, via `extract_recipe`. Because of Pydantic's role, you know that even scraped blog content will be mapped into a predictable and reliable data structure.

The server handles structured food and nutritional data. The specific types include ingredient lists, nutrient profiles (`get_recipe_nutrition`), and general recipe metadata.

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