How to Use the FatSecret Platform MCP in Pydantic AI

Q: How do I initialize the FatSecret Platform toolset in Pydantic AI?

Use the unified MCPToolset constructor with your Vinkius HTTP endpoint. Pass this toolset to your agent's toolsets argument during initialization.

Run type-safe nutritional audits in Pydantic AI with guaranteed schema validation on every query.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect FatSecret Platform MCP to Pydantic AI

Create your Vinkius account to connect FatSecret Platform to Pydantic AI and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup FatSecret Platform with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate raw barcode data in Pydantic AI.

The `get_food_by_barcode` tool retrieves nutritional profiles that are immediately validated against Pydantic models at runtime. If the FatSecret database returns a weirdly formatted UPC response, your agent catches it before it corrupts your database. This strict validation prevents silent failures in your food logging pipelines. Since this MCP Server handles the raw API connection, the Pydantic AI framework only focuses on type-checking the returned data.

Parse complex recipes via this MCP Server.

The `get_recipe_details` tool returns deep nested structures of ingredients, measurements, and cooking instructions. Your Pydantic AI agent maps these structures to strict Python types, ensuring your application never crashes on a missing field. This makes recipe parsing predictable. If you are building a meal planning app, you can rely on the fact that every ingredient list matches your expected schema exactly.

Validate search results with Pydantic AI.

The `search_foods` tool lets your agent query the database and receive structured lists of matching items. The framework validates every search result, ensuring that fields like calories and protein are always floats, not strings. This level of safety is crucial for clinical or research applications using this MCP Server. You can swap out underlying LLMs without worrying that a different model will hallucinate the structure of the nutritional data.

Setup guide

Set up FatSecret Platform 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": {
        "fatsecret-platform-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent FatSecret Platform 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 FatSecret Platform. 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 FatSecret Platform 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 FatSecret Platform MCP in Pydantic AI

The framework raises a validation error immediately. This prevents your agent from processing corrupted data or passing broken nutritional values to your database.

Use the unified `MCPToolset` constructor with your Vinkius HTTP endpoint. Pass this toolset to your agent's `toolsets` argument during initialization.

Yes. Pydantic AI is model-agnostic, meaning you can run local models or commercial APIs to search and analyze recipes using `search_recipes`.

Yes. Vinkius hosts and manages the server for you, so your Pydantic AI code only needs to connect to the provided HTTP endpoint.

We run the FatSecret Platform MCP Server inside an isolated V8 sandbox. Your specific search queries, recipe IDs, and nutrient lookups are processed ephemerally and never written to disk.

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