How to Use the Gatling MCP in Mastra AI

Q: How do I retry a failed Gatling run in Mastra AI?

Configure a Mastra AI workflow step that calls startsimulation. If it fails, the built-in retry engine waits and checks listpools before trying again.

Q: Can Mastra AI automatically stop a Gatling simulation?

Yes. Your workflow can monitor performance via getrun and call abortsimulation if error rates spike.

Q: How do I choose the right team for a Gatling run in Mastra AI?

Use listteams inside your agent's system prompt. The Mastra AI agent will select the correct team ID before triggering any simulation.

Q: How does this MCP Server handle simulation metadata?

The server calls getsimulation to fetch scenario configurations. Your agent reads the virtual user profiles and assertions to verify test parameters.

Q: How does Mastra AI protect my Gatling simulation configurations?

All calls to getsimulation run within this MCP Server's sandbox. Your team IDs and test configurations are processed in memory and are never cached or stored on external disks.

Automate complex load testing workflows and retry failed Gatling runs using Mastra AI agents.

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 Mastra AI

Create your Vinkius account to connect Gatling to Mastra AI 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 Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Branch workflows based on Gatling runs

The `get_run` tool retrieves execution metrics that your Mastra AI workflow uses to make real-time routing decisions. If a run shows error rates above your threshold, the agent automatically triggers a rollback workflow. You can write a step that checks `list_runs` to compare the last three executions. If performance degrades sequentially, the workflow stops future deployments and pings your on-call team.

Manage simulator pools with this MCP Server

The `list_pools` tool provides the current capacity of your load generators so your Mastra AI agent can select the best region. If a pool is saturated, the workflow branches to try another region or waits for queue clearance. Your agent uses `start_simulation` only after confirming pool availability. This prevents your automated pipelines from failing due to resource limits on Gatling Enterprise.

Automate package validation in Mastra AI

The `list_packages` tool identifies compiled test artifacts to ensure your agent deploys the correct simulation code. The workflow matches the package with the correct team using `list_teams` before starting execution. If a package is missing, the agent halts the pipeline. By combining this MCP Server with Mastra AI's retry logic, transient API errors won't break your test runs.

Setup guide

Set up Gatling MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All Gatling tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "gatling-mcp-client",
  servers: {
    "gatling-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Gatling Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Gatling tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Gatling transactions"
);
console.log(result.text);

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 Mastra AI

Configure a Mastra AI workflow step that calls `start_simulation`. If it fails, the built-in retry engine waits and checks `list_pools` before trying again.

Yes. Your workflow can monitor performance via `get_run` and call `abort_simulation` if error rates spike.

Use `list_teams` inside your agent's system prompt. The Mastra AI agent will select the correct team ID before triggering any simulation.

The server calls `get_simulation` to fetch scenario configurations. Your agent reads the virtual user profiles and assertions to verify test parameters.

All calls to `get_simulation` run within this MCP Server's sandbox. Your team IDs and test configurations are processed in memory and are never cached or stored on external disks.

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