How to Use the Gatling MCP in Claude

Q: How does Claude Desktop show Gatling run details?

The agent uses getrun to pull metrics like request counts and error rates. Claude Desktop displays these metrics as they update. It gives you a clear snapshot of performance without opening the web console.

Q: How do I find my Gatling simulation IDs?

Ask your agent to list them, and it runs listsimulations to fetch all available scenarios. Claude Desktop shows the IDs, names, and team associations. You can then use these IDs to start your next test run.

Run Gatling simulations and monitor load tests directly from Claude Desktop without switching to the Enterprise dashboard.

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 Claude Desktop

Create your Vinkius account to connect Gatling to Claude Desktop 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 Claude Desktop

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run Gatling tests directly inside Claude Desktop

The `start_simulation` tool triggers load tests on Gatling Enterprise, while `get_run` checks the real-time status of your active runs. Tell Claude Desktop to spin up a scenario and it kicks off the runner immediately. You get the exact run ID in your chat window, letting you monitor the load generation progress without opening a browser tab. Using `abort_simulation` lets your agent kill a run if error rates spike. If a test goes sideways, just tell Claude Desktop to stop the run to save your cloud budget. You keep complete control over your test cycles right from your local workspace.

Inspect simulations and packages using this MCP Server

The `list_simulations` and `list_packages` tools retrieve your active test setups and uploaded binaries from Gatling Enterprise. Claude Desktop reads these details to confirm you are targeting the correct class name and simulation file. This prevents you from running stale code or targeting the wrong test scenario. By pulling simulation details via `get_simulation`, your agent identifies which virtual user profiles are configured. You can ask Claude Desktop if a scenario uses the right load steps before you execute it. It's a quick way to verify your configurations are correct before hammering your servers.

Check load generator pools before starting runs

The `list_pools` tool pulls the current load generator pools, and `list_teams` maps the correct team associations to your Gatling Enterprise account. Claude Desktop checks these pools to ensure you have active generators ready to handle the traffic. You avoid running into resource starvation issues during high-volume testing. This MCP Server exposes these infrastructure limits directly to your agent. If a specific pool is saturated, Claude Desktop suggests switching teams or choosing a different region. It keeps your pipeline moving without manual infrastructure checks.

Setup guide

Set up Gatling MCP in Claude Web or Desktop

1

Open Claude Settings

Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.
2

Add Custom Connector

Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL: https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. For OAuth-protected servers, expand Advanced settings to add credentials.
3

Start a conversation

Open a new chat. The Gatling MCP tools are available immediately — no restart needed.

Endpoint URL

https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

No configuration file needed — paste the URL directly in the Claude web interface.

Available on Free (1 connector), Pro, Max, Team, and Enterprise plans.

Prerequisites

Claude Desktop installed (macOS or Windows)
Active Vinkius subscription with a valid endpoint token

1

Open Claude Desktop Settings

Click the menu icon at the top-left corner, go to Settings → Developer → Edit Config. This opens claude_desktop_config.json in your default text editor.
2

Paste the Gatling MCP configuration

Copy the JSON snippet on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Desktop

Close and reopen the application. Claude needs a full restart to load new MCPs — refreshing a conversation is not enough.
4

Verify the connection

Open a new conversation. Click the 🔌 icon at the bottom of the message input. You should see tools listed under gatling-mcp.

json

{
  "mcpServers": {
    "gatling-mcp": {
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

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 Claude Desktop

You ask Claude Desktop to run a test, which prompts the agent to call the `start_simulation` tool. It returns the active run ID directly in your chat. From there, you can monitor the run status without leaving the app.

Yes, you can stop any active run. Tell Claude Desktop to kill the simulation, and it executes `abort_simulation` using the active run ID. This stops the load generators immediately to protect your test environment.

The agent uses `get_run` to pull metrics like request counts and error rates. Claude Desktop displays these metrics as they update. It gives you a clear snapshot of performance without opening the web console.

Ask your agent to list them, and it runs `list_simulations` to fetch all available scenarios. Claude Desktop shows the IDs, names, and team associations. You can then use these IDs to start your next test run.

Vinkius runs the server in an isolated sandbox, keeping your Gatling API tokens completely secure. Your local Claude Desktop client talks to Vinkius via a secure endpoint token. The raw API tokens are never exposed to the LLM or stored in plain text.

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