How to Use the Metabolic Energy Estimator MCP in OpenAI Agents SDK

Q: How does the Metabolic Energy Estimator prevent hallucinated exercises in OpenAI Agents SDK?

It forces the agent to call searchactivitycatalog first to obtain a valid activity ID. The OpenAI Agents SDK then validates this ID before running estimatecaloriesburned, keeping your calculations accurate.

Q: Does this MCP Server support dynamic metabolic adaptation?

Yes, the calculateweightlossprojection tool applies a metabolic decay factor for timelines over six weeks. This prevents the agent from promising unrealistic weight loss based on static baselines.

Run deterministic metabolic math in production with the Metabolic Energy Estimator and OpenAI Agents SDK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Metabolic Energy Estimator MCP to OpenAI Agents SDK

Create your Vinkius account to connect Metabolic Energy Estimator to OpenAI Agents SDK 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 Metabolic Energy Estimator with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Project weight loss timelines with adaptive decay

The `calculate_weight_loss_projection` tool calculates exact timelines to target weights based on daily deficits, factoring in adaptive thermogenesis for long-term accuracy. By running this calculation locally, your OpenAI Agents SDK pipelines get reliable, decay-adjusted projections from this MCP Server instead of linear estimates that fail after six weeks. Your agent uses these realistic timelines to configure user expectations in production health trackers. Tracing logs in your OpenAI dashboard show the exact calorie math behind every projection, ensuring your system remains accountable and safe without relying on external health APIs.

Calculate TDEE and BMR with zero-config discovery

The `calculate_tdee` tool executes the Mifflin-St Jeor equation to establish baseline metabolic rates directly inside your OpenAI Agents SDK agent. Your system auto-discovers this tool instantly, skipping complex integration code and letting your agent calculate energy targets right out of the box. Setting cacheToolsList to true keeps these metabolic lookups lightning fast during multi-agent conversations. When a user inputs their weight and height, the agent calculates their active baseline and passes the values to downstream agents for dietary planning.

Search physical activities using the local MCP catalog

The `search_activity_catalog` tool queries a built-in database of eighty physical activities to retrieve exact MET values for your OpenAI Agents SDK agent. To calculate actual energy output, the agent feeds these IDs directly into `estimate_calories_burned` alongside user weight and duration. Guardrails in this python SDK validate that the agent only executes calculations with valid catalog IDs, preventing hallucinated exercises. This strict check ensures that every logged calorie burn is backed by deterministic metabolic science before it hits your production database.

Setup guide

Set up Metabolic Energy Estimator MCP in OpenAI Agents SDK

Prerequisites

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

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Metabolic Energy Estimator tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Metabolic Energy Estimator tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Metabolic Energy Estimator tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Metabolic Energy Estimator Agent",
            instructions="You have access to Metabolic Energy Estimator tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 calorie-burn-estimator. 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 Metabolic Energy Estimator 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 Metabolic Energy Estimator MCP in OpenAI Agents SDK

It forces the agent to call `search_activity_catalog` first to obtain a valid activity ID. The OpenAI Agents SDK then validates this ID before running `estimate_calories_burned`, keeping your calculations accurate.

Yes. You initialize the MCP server using the streamable HTTP transport inside an async context manager. This setup allows your agent to handle hundreds of concurrent TDEE calculations without blocking.

You register the MCP server URL using MCPServerStreamableHttpParams and pass the resulting server object in the mcp_servers list. The OpenAI Agents SDK automatically registers `calculate_tdee` and the other tools.

Yes, the `calculate_weight_loss_projection` tool applies a metabolic decay factor for timelines over six weeks. This prevents the agent from promising unrealistic weight loss based on static baselines.

This server is entirely stateless and never stores your users' weight, height, or activity logs. Every parameter passed to `calculate_tdee` is processed in memory inside the V8 sandbox and immediately 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