How to Use the FatSecret MCP in CrewAI

Q: How do I connect the FatSecret MCP Server to CrewAI?

Install the tools package first using pip install crewai "crewaitools". Then, pass the Vinkius SSE endpoint URL directly into your Agent configuration using the mcps parameter. Your agents will automatically discover the tools and start querying food data.

Q: How does CrewAI handle serving size variations from FatSecret?

The getfatsecretfooddetails tool returns a structured list of all available serving sizes, including grams, cups, and ounces. Your agent can read this list and select the specific unit required for its calculations. This prevents errors when agents build custom meal plans.

Give your CrewAI agents direct access to the FatSecret food database to track macros and analyze diets autonomously.

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 CrewAI

Create your Vinkius account to connect FatSecret to CrewAI 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 CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Let CrewAI agents run deep nutritional audits

Your researcher agent uses `search_fatsecret_foods` to pull raw ingredient matches instantly from the database. Specialized agents need this hard data to build meal plans without human intervention. Once the matches come back, your analyzer agent uses `get_fatsecret_food_details` to verify exact macro splits across different serving sizes like grams or ounces. The crew processes these details in shared memory to adjust dietary recommendations on the fly.

Build autonomous dietary monitors with this MCP Server

This MCP Server exposes the FatSecret tools directly to your crew so agents can query `search_fatsecret_foods` to cross-reference logged meals. You can set up a multi-agent loop where one agent flags food logs and another corrects them. If a user logs something vague, a moderator agent steps in to query `get_fatsecret_food_details`. It pulls the exact serving sizes to fix the entry before saving it. Your entire pipeline runs without hitting manual bottlenecks.

Resolve complex nutritional calculations in parallel

Agents invoke `get_fatsecret_food_details` simultaneously to compare different brands of the same food item. Hierarchical crews work best when they don't have to wait on slow API wrappers to calculate exact protein, carb, and fat ratios. Your supervisor agent coordinates this workflow by dividing the search terms. Each sub-agent runs `search_fatsecret_foods` for its assigned ingredient, feeding the structured JSON back up the chain for final assembly.

Setup guide

Set up FatSecret MCP in CrewAI

Prerequisites

Python 3.10+ installed
crewai package (pip install crewai)
Active Vinkius subscription with a valid endpoint token

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke FatSecret tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="FatSecret Analyst",
    goal="Access and analyze FatSecret data via MCP.",
    backstory="Expert analyst with direct FatSecret access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent FatSecret transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

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

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="FatSecret Analyst",
        goal="Access and analyze FatSecret data via MCP.",
        backstory="Expert analyst with direct FatSecret access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent FatSecret transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 CrewAI

Install the tools package first using `pip install crewai "crewai[tools]"`. Then, pass the Vinkius SSE endpoint URL directly into your Agent configuration using the `mcps` parameter. Your agents will automatically discover the tools and start querying food data.

Yes, your agents can find both generic and branded food items. The `search_fatsecret_foods` tool queries the entire global database to return matching options. From there, your agent can pick the exact brand match to analyze.

The `get_fatsecret_food_details` tool returns a structured list of all available serving sizes, including grams, cups, and ounces. Your agent can read this list and select the specific unit required for its calculations. This prevents errors when agents build custom meal plans.

No, you do not need to deal with authentication inside your agent code. Vinkius handles the entire FatSecret OAuth flow on its secure backend. Your crew only needs the single MCP endpoint token to run queries.

All food queries, food IDs, and macro records are processed inside an ephemeral V8 Isolate Sandbox on Vinkius. We use a zero-trust model, meaning your data is never stored or used to train models. Once the execution finishes, the environment is destroyed.

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