How to Use the Gatling MCP in Google ADK

Q: Can my Google ADK agent automate Gatling performance tests?

Yes. The agent can use the startsimulation tool from this MCP server to begin a test and getrun to fetch the results, which can then be pushed to BigQuery for analysis.

Q: How does the Google ADK agent find the right Gatling simulation to run?

The agent can call listsimulations, which returns names, IDs, and team associations. It can then use that information to pick the correct simulation ID to pass to startsimulation.

Q: How do I prevent my Google ADK agent from overloading my Gatling setup?

Before calling startsimulation, have your agent use the listpools tool. This checks the status of the load generator pools so you don't start a test you don't have the capacity for.

Connect Google ADK to Gatling Enterprise for performance analysis against your BigQuery datasets.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Gatling MCP to Google ADK

Create your Vinkius account to connect Gatling 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 Gatling with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Trigger Tests from Cloud Events

Your Google ADK agent can listen for a Pub/Sub message or a new Cloud Build trigger, then automatically call `start_simulation` through this MCP Server. This connects your CI/CD process directly to your performance testing suite. After getting a run ID back, the agent can poll `get_run` and write the performance metrics directly into a BigQuery table. Gemini's long context helps the agent understand the history of runs before deciding what to do next.

Analyze Performance with Google ADK

This is where the Google ADK integration pays off. Your agent can fetch Gatling results with `get_run` and simultaneously pull monitoring data from Google Cloud Monitoring for the same time window. By combining these two data sources, the agent can identify correlations between application performance and infrastructure load. It can use `list_runs` to get historical context and spot regressions that a simple pass/fail check would miss.

Manage Resources via your MCP Server

Before kicking off a new performance test, your agent should check for available capacity. It uses `list_pools` to see the status of your load generators, preventing tests from failing because resources are tied up. You can also build agents that manage your Gatling environment. For instance, an agent could use `list_teams` and `list_packages` to audit simulation scripts or use `list_tokens` to flag API tokens that are about to expire.

Setup guide

Set up Gatling 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 Gatling 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="Gatling_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Gatling 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 Gatling. 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 Gatling 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 Gatling MCP in Google ADK

Yes. The agent can use the `start_simulation` tool from this MCP server to begin a test and `get_run` to fetch the results, which can then be pushed to BigQuery for analysis.

The agent can call `list_simulations`, which returns names, IDs, and team associations. It can then use that information to pick the correct simulation ID to pass to `start_simulation`.

Before calling `start_simulation`, have your agent use the `list_pools` tool. This checks the status of the load generator pools so you don't start a test you don't have the capacity for.

Yes, the Google ADK lets you filter the tools exposed to the agent. You could grant access to `list_simulations` and `get_run` but not `start_simulation` to create a read-only monitoring agent.

It only handles Gatling Enterprise metadata—like simulation names, package details, and performance run statistics. Your application's internal data is never seen or stored. Each request is isolated in a zero-trust sandbox.

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