How to Use the FatSecret MCP in Pydantic AI

Build type-safe fitness agents with Pydantic AI that validate FatSecret food schemas at runtime to prevent silent data corruption.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect FatSecret MCP to Pydantic AI

Create your Vinkius account to connect FatSecret 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 with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate FatSecret macros with Pydantic AI

The `get_fatsecret_food_details` tool returns strict JSON payloads containing calorie, protein, fat, and carb data. Pydantic AI validates these incoming nutritional facts against your Python models at runtime, failing loudly if the API structure changes. This prevents silent data corruption in your database. You get guaranteed type safety for every serving size and macro count your agent processes.

Search food items with type-safe schemas

The `search_fatsecret_foods` tool exposes the massive FatSecret food index to your agent using structured MCP schemas. Pydantic AI maps the search results directly to your defined models, ensuring every calorie count is an integer and every food name is a string. You register the toolset using the unified HTTP constructor. This connects your agent to the food database with zero manual JSON parsing.

Maintain runtime correctness during food queries

The `get_fatsecret_food_details` tool ensures your agent has access to all serving sizes for precise logging. Because Pydantic AI is model-agnostic, you can swap your LLM provider while keeping your nutritional validation logic completely intact. The server runs externally, and your agent connects via SSE or HTTP. This decoupled setup keeps your validation layer lightweight and fast.

Setup guide

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

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

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

Pydantic AI raises a validation error if the FatSecret API returns data that violates your model. You can catch these exceptions in your agent loop to handle unexpected API changes gracefully.

Use the MCPToolset class with your Vinkius HTTP endpoint. Pass this toolset to the agent's toolsets parameter to automatically expose both food search and details tools.

Yes, you can use the SSE transport to handle real-time data streaming. This is ideal for keeping your agent responsive during complex food database searches.

You can use any LLM supported by Pydantic AI, including OpenAI, Anthropic, or local models. The framework handles the schema translation and validation regardless of the backend model.

All data passes through a secure MCP gateway using ephemeral V8 isolates. Your food search queries and macro details are never saved to disk, ensuring strict user privacy.

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