How to Use the ExerciseDB MCP in Google ADK

Q: How do I initialize the ExerciseDB MCP Server in Google ADK?

Run pip install google-adk to get the framework. Use McpToolset with StreamableHttpServerParameters pointing to your Vinkius URL, and pass that toolset into your LlmAgent configuration.

Q: What happens if my agent requests an invalid body part or equipment name?

Your agent should first call getbodypartlist or getequipmentlist to discover valid parameters. This metadata-first approach prevents bad API requests and keeps your agent's execution path clean.

Connect Gemini to 1,300+ movements using Google ADK and our ExerciseDB MCP Server to build enterprise fitness applications.

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 Google ADK

Create your Vinkius account to connect ExerciseDB to Google ADK 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 Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Connect Google ADK to the ExerciseDB MCP Server

`get_all_exercises` serves as the foundation for feeding clean, structured movement data into Gemini's massive one-million-token context window. You can pull extensive lists of target muscles, required gear, and animated demonstration links. The framework processes this data alongside your existing enterprise datasets. Setting up the connection requires minimal code. You instantiate `McpToolset` with your Vinkius HTTP URL and pass it to your `LlmAgent`. Gemini immediately gains the ability to parse complex workout requests and match them to real-world movements.

Filter movements by equipment and target muscles

`get_exercises_by_equipment` and `get_exercises_by_target` allow your agent to build highly targeted training programs. If your enterprise app connects to a gym's inventory database in BigQuery, the agent cross-references available machines with valid equipment types. It only suggests movements the user can actually perform. This direct targeting prevents the LLM from suggesting exercises that require missing gear. By combining Google Cloud data sources with these precise filters, your agent delivers highly practical routines that match real-world constraints.

Search and identify specific exercises instantly

`get_exercises_by_name` and `get_exercise_by_id` provide instant access to individual movement profiles. When a user searches for a specific variation, the agent calls these tools to return exact step-by-step instructions and demonstration GIFs. It bypasses broad searches to fetch exactly what was requested. You can restrict which tools are exposed using the optional `tool_names` filter in the ADK. If you only want your agent to handle equipment-based queries, you can limit access to keep the agent focused and efficient.

Setup guide

Set up ExerciseDB MCP in Google ADK

Prerequisites

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

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with ExerciseDB tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="ExerciseDB_agent",
    model="gemini-2.0-flash",
    instruction="You have access to ExerciseDB tools via MCP.",
    tools=mcp_tools,
)

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 Google ADK

Run `pip install google-adk` to get the framework. Use `McpToolset` with `StreamableHttpServerParameters` pointing to your Vinkius URL, and pass that toolset into your `LlmAgent` configuration.

Yes. Because the ADK integrates natively with Google Cloud, your agent can pull gym inventory from BigQuery and use `get_exercises_by_equipment` to filter workouts based on what machines are actually on the gym floor.

Yes, the framework supports both connection methods. For cloud-deployed enterprise agents, the streamable HTTP transport through Vinkius is the recommended approach.

Your agent should first call `get_body_part_list` or `get_equipment_list` to discover valid parameters. This metadata-first approach prevents bad API requests and keeps your agent's execution path clean.

No. The server only processes read-only exercise names, anatomical targets, and instructional GIF links. Your users' actual workout logs and private physical metrics remain securely inside your Google Cloud 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