How to Use the ExerciseDB MCP in OpenAI Agents SDK

Q: How do I connect the ExerciseDB MCP Server to the OpenAI Agents SDK?

Install the package using pip install openai-agents in your environment. Initialize the server using MCPServerStreamableHttp with your Vinkius endpoint URL, then pass it directly into your Agent constructor using the mcpservers parameter.

Q: Can I trace ExerciseDB MCP Server API calls made by the OpenAI Agents SDK?

Every tool invocation, such as calling getexercisesbyname, shows up in your OpenAI developer dashboard. You can monitor latency, payload sizes, and agent decisions in real time.

Q: How does the agent handle pagination when fetching the full exercise list?

The getallexercises tool supports limit and offset parameters. Your agent uses these parameters to fetch data in small batches, preventing memory overload and high latency.

Build production fitness agents with OpenAI Agents SDK and our managed MCP Server to safely fetch over 1,300 verified exercises.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect ExerciseDB MCP to OpenAI Agents SDK

Create your Vinkius account to connect ExerciseDB 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 ExerciseDB with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Safely query the MCP Server with OpenAI Agents SDK

`get_all_exercises` retrieves names, body parts, targets, and equipment with built-in pagination limits. Your agent uses these details to map workouts without hitting API payload bottlenecks. It pulls step-by-step instructions and animated GIF URLs directly into your runtime. Because the OpenAI Agents SDK manages these calls through a streamable HTTP connection, you get instant validation before execution. The platform traces every exercise request on your dashboard, keeping your production agent within strict safety guardrails.

Target specific muscle groups and equipment

`get_exercises_by_target` and `get_exercises_by_equipment` filter the database down to what your user actually needs. If a user only has dumbbells, the agent uses these tools to ignore barbell or cable movements entirely. It prevents the model from hallucinating non-existent gear or impossible body mechanics. You can set up specialized agents for different training styles. One agent handles cardio using `get_exercises_by_body_part`, while another handles strength. The SDK manages the handoffs between these specialized agents without dropping the context of the user's physical limits.

Discover valid biomechanical parameters

`get_body_part_list`, `get_equipment_list`, and `get_target_list` let your agent discover valid database parameters at runtime. Instead of hardcoding muscle names or equipment types, your code queries these endpoints to build dynamic, error-free filters. This prevents empty search results when users ask for obscure variations. Caching these lists is straightforward. Set `cacheToolsList=True` in your configuration to keep response times low and avoid unnecessary roundtrips. Your agent stays fast, responsive, and accurate during high-traffic workout generation sessions.

Setup guide

Set up ExerciseDB 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 ExerciseDB tools at runtime.
3

Create your Agent

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

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate ExerciseDB 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="ExerciseDB Agent",
            instructions="You have access to ExerciseDB 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 ExerciseDB. 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 ExerciseDB 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 ExerciseDB MCP in OpenAI Agents SDK

Install the package using `pip install openai-agents` in your environment. Initialize the server using `MCPServerStreamableHttp` with your Vinkius endpoint URL, then pass it directly into your Agent constructor using the `mcp_servers` parameter.

Yes, the SDK automatically discovers all nine tools from the server. Your agent immediately knows how to call `get_exercise_by_id` or search by name without you writing manual JSON schemas.

Every tool invocation, such as calling `get_exercises_by_name`, shows up in your OpenAI developer dashboard. You can monitor latency, payload sizes, and agent decisions in real time.

The `get_all_exercises` tool supports limit and offset parameters. Your agent uses these parameters to fetch data in small batches, preventing memory overload and high latency.

This server only processes public exercise metadata, instructions, and GIF URLs. No personal user metrics, workout logs, or private health data ever touch the server or the Vinkius hosting environment.

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