How do I get an ExerciseDB API key?

Sign up on [**RapidAPI**](https://rapidapi.com/justin-w-fns/api/exercisedb) and subscribe to the ExerciseDB API. Free tier includes 10 requests/day. Paid plans offer more requests.

What body parts are available?

The database includes: back, chest, shoulders, upper arms, lower arms, upper legs, lower legs, neck, waist and cardio. Use get_body_part_list to see the complete list.

Does the API include exercise instructions?

Yes! Each exercise includes step-by-step instructions (numbered list) and an animated GIF URL showing the proper form and movement.

ExerciseDB MCP Server for OpenAI Agents SDK 9 tools — connect in under 2 minutes

Name: ExerciseDB
Availability: InStock
Author: Vinkius

openai.github.io/openai-agents-python/mcp

Built by Vinkius GDPR 9 Tools SDK

The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect ExerciseDB through Vinkius and your agents gain typed, auto-discovered tools with built-in guardrails. no manual schema definitions required.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

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

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    async with MCPServerStreamableHttp(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as mcp_server:

        agent = Agent(
            name="ExerciseDB Assistant",
            instructions=(
                "You help users interact with ExerciseDB. "
                "You have access to 9 tools."
            ),
            mcp_servers=[mcp_server],
        )

        result = await Runner.run(
            agent, "List all available tools from ExerciseDB"
        )
        print(result.final_output)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About ExerciseDB MCP Server

Connect to ExerciseDB and explore a comprehensive exercise database through natural conversation.

The OpenAI Agents SDK auto-discovers all 9 tools from ExerciseDB through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries ExerciseDB, another analyzes results, and a third generates reports, all orchestrated through Vinkius.

What you can do

Exercise Search — Browse 1300+ exercises with detailed instructions and animated GIFs
Filter by Body Part — Find exercises for back, chest, shoulders, legs, arms, waist and more
Filter by Target Muscle — Search exercises targeting specific muscles (abs, biceps, quads, glutes)
Filter by Equipment — Find exercises by equipment type (dumbbell, barbell, body weight, cable)
Search by Name — Find exercises by name (crunches, curls, presses, squats)
Reference Lists — Get complete lists of body parts, target muscles and equipment types

The ExerciseDB MCP Server exposes 9 tools through the Vinkius. Connect it to OpenAI Agents SDK in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect ExerciseDB to OpenAI Agents SDK via MCP

Follow these steps to integrate the ExerciseDB MCP Server with OpenAI Agents SDK.

Install the SDK

Run pip install openai-agents in your Python environment

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com

Run the script

Save the code above and run it: python agent.py

Explore tools

The agent will automatically discover 9 tools from ExerciseDB

Why Use OpenAI Agents SDK with the ExerciseDB MCP Server

OpenAI Agents SDK provides unique advantages when paired with ExerciseDB through the Model Context Protocol.

Native MCP integration via `MCPServerSse`, pass the URL and the SDK auto-discovers all tools with full type safety

Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure

Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate

First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output

ExerciseDB + OpenAI Agents SDK Use Cases

Practical scenarios where OpenAI Agents SDK combined with the ExerciseDB MCP Server delivers measurable value.

Automated workflows: build agents that query ExerciseDB, process the data, and trigger follow-up actions autonomously

Multi-agent orchestration: create specialist agents. one queries ExerciseDB, another analyzes results, a third generates reports

Data enrichment pipelines: stream data through ExerciseDB tools and transform it with OpenAI models in a single async loop

Customer support bots: agents query ExerciseDB to resolve tickets, look up records, and update statuses without human intervention

ExerciseDB MCP Tools for OpenAI Agents SDK (9)

These 9 tools become available when you connect ExerciseDB to OpenAI Agents SDK via MCP:

get_all_exercises

Returns exercise names, body parts, target muscles, equipment needed, GIF URLs and step-by-step instructions. Supports limit and offset parameters for pagination. Get all exercises with pagination

get_body_part_list

Useful for discovering valid body part values to use with get_exercises_by_body_part. Get list of all body parts

get_equipment_list

Useful for discovering valid equipment values to use with get_exercises_by_equipment. Get list of all equipment types

get_exercise_by_id

Returns exercise name, body part, target muscle, equipment, secondary muscles, step-by-step instructions and animated GIF URL. Get a specific exercise by ID

get_exercises_by_body_part

Common body parts include: "back", "chest", "shoulders", "upper arms", "lower arms", "upper legs", "lower legs", "neck", "waist", "cardio". Returns exercise details with target muscles, equipment and instructions. Get exercises by body part

get_exercises_by_equipment

Common equipment includes: "assisted", "band", "barbell", "body weight", "bosu ball", "cable", "dumbbell", "elliptical machine", "ez barbell", "hammer", "kettlebell", "leverage machine", "medicine ball", "olympic barbell", "resistance band", "roller", "rope", "skierg machine", "sled machine", "smith machine", "stability ball", "stationary bike", "stepmill machine", "tire", "trap bar", "upper body ergometer", "weighted", "wheel roller". Returns exercise details with body part, target muscles and instructions. Get exercises by equipment type

get_exercises_by_name

Returns matching exercises with full details including body part, target muscles, equipment, instructions and GIF URLs. Get exercises by name search

get_exercises_by_target

Common targets include: "abductors", "abs", "adductors", "biceps", "calves", "cardiovascular system", "delts", "forearms", "glutes", "hamstrings", "lats", "levator scapulae", "pectorals", "quads", "serratus anterior", "spine", "traps", "triceps", "upper back". Returns exercise details with body part, equipment and instructions. Get exercises by target muscle

get_target_list

Useful for discovering valid target values to use with get_exercises_by_target. Get list of all target muscles

Example Prompts for ExerciseDB in OpenAI Agents SDK

Ready-to-use prompts you can give your OpenAI Agents SDK agent to start working with ExerciseDB immediately.

"Show me exercises for chest with dumbbells."

"What exercises target the abs?"

"Show me exercises I can do with just body weight."

Troubleshooting ExerciseDB MCP Server with OpenAI Agents SDK

Common issues when connecting ExerciseDB to OpenAI Agents SDK through the Vinkius, and how to resolve them.

MCPServerStreamableHttp not found

Ensure you have the latest version: pip install --upgrade openai-agents

Agent not calling tools

Make sure your prompt explicitly references the task the tools can help with.

ExerciseDB + OpenAI Agents SDK FAQ

Common questions about integrating ExerciseDB MCP Server with OpenAI Agents SDK.

How does the OpenAI Agents SDK connect to MCP?

Use MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.