How to Use the FatSecret Platform MCP in AutoGen

Let AutoGen agents debate nutritional plans and verify macros using the live FatSecret Platform database.

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 AutoGen

Create your Vinkius account to connect FatSecret Platform to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Verify FatSecret Platform data via AutoGen debate

Diet planning is subjective, but nutritional facts aren't. This MCP Server allows you to set up an AutoGen conversation where a meal planner agent proposes recipes via `search_recipes`, while a strict dietitian agent audits the ingredients using `get_food_details` to ensure they meet caloric limits. The agents debate until they reach a consensus. Instead of relying on a single model's guess, they cross-reference the live database, arguing over macro distributions and ingredient swaps before presenting a finalized, verified meal plan to the user.

Audit packaged foods with specialized agents

Put your agents to work on complex data validation. You can set up an AutoGen workflow where a scanner agent processes a barcode using `get_food_by_barcode`, and a separate compliance agent checks the returned allergen data against a user's health profile. This separation of concerns prevents errors. The compliance agent can challenge the scanner agent's recommendations, forcing a deeper query using `list_food_categories` to find safer alternatives if a high-risk ingredient is detected in the food details.

Coordinate complex recipe analysis

Analyzing a recipe requires multiple steps. With this setup, one AutoGen agent can fetch the raw recipe steps using `get_recipe_details`, while another agent concurrently searches for the individual ingredient profiles using `search_foods`. They collaborate to calculate the exact nutritional density per serving. By dividing the labor, your agents complete the analysis faster and verify each other's math against the actual API data before saving the results.

Setup guide

Set up FatSecret Platform 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 FatSecret Platform 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="FatSecret Platform_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent FatSecret Platform 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="FatSecret Platform_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent FatSecret Platform 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 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 AutoGen

You use the extension package. Run pip install -U autogen-ext[mcp], configure the MCP client with your Vinkius endpoint, and pass the resulting tools list directly to your AssistantAgent constructor.

Yes, they share the toolset. Any agent in your AutoGen group chat can invoke tools like get_food_details or search_recipes as needed, allowing them to share nutritional data and debate the results in real-time.

It handles the schema translation automatically. The adapter converts the FatSecret Platform tool definitions into the exact JSON schema format that AutoGen's AssistantAgent expects, so you don't have to write manual wrapper functions.

Yes, you can structure a debate around barcodes. One agent can call get_food_by_barcode to fetch the raw product data, while another agent analyzes the macros to debate whether the food fits into the user's target diet.

Absolutely. Your API requests, including food searches and recipe IDs, are routed through a zero-trust, ephemeral sandbox. No raw nutritional queries or database keys are stored on Vinkius, ensuring complete data 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