MCP SERVER

Pilot Gatling Enterprise Edition from your coding agent.

Query your account, analyze runs, share results, and start tests, all from natural language, without leaving your IDE.

Check your inbox We just sent the getting started guide to your email.

AVAILABLE FOR

MCP SERVER

Give your coding agent full control of Gatling Enterprise Edition

The MCP server is a local server that runs on your machine and exposes your Gatling Enterprise Edition account to any MCP-compatible AI client. Read, analyze, share, and pilot, all from natural language.

Read anything in your account

Stop context-switching to check a dashboard. Ask what teams you're on, what's deployed, where you can run tests... Get a real answer, live from your account.

Example tools: teams.read_all, packages.read_all, tests.read_all, locations.read_all, runs.read_all

Manage all source repos for your tests

Register a git repository as a source your tests can build from, list what's already registered, or remove one.

Example tools: source_repositories.create_one, source_repositories.read_all, source_repositories.delete_one

Analyze your runs

Go beyond a pass/fail status and get the actual diagnosis. Ask why a run failed and your agent cross-references the logs against the performance report to tell you: build error, injection crash, or stop-criteria breach.

Example tools: runs.read_status, runs.read_run_logs, runs.read_report_requests

Share results

One request, one link. Send a run's dashboard to anyone on the team.

Example tools: runs.create_public_link

Know which tool to use, and when

Your agent doesn't just get access to these tools, it gets guided on how to use them. The gatling-mcp skill documents the terminology, the required role for each action, and the recommended workflows, so your agent picks the right tool the first time.

Ready to get started?
Receive the guide to start using the MCP

Check your inbox We just sent the getting started guide to your email.

YOUR NEW END-TO-END WORKFLOW

Write a test. Ask your coding agent to run it, diagnose it, and share it.

Write your load test

Author your load test in Java, Kotlin, Scala, or JavaScript, in your IDE.

Ask your coding agent to configure, deploy, and start it

‍Your coding agent fetches your live account data (teams, locations, packages), configures the test, builds the package, deploys it to Gatling Enterprise Edition, and starts the run.

Ask your coding agent what happened

‍Your agent cross-references the run's logs against its performance report to tell you why it failed: build error, injection crash, or stop-criteria breach.

Ask your coding agent to share it

One request generates a public link.

MCP Server

See the MCP server in action

Explore how you can query your tests and packages, find the right teams and
locations, and configure a deployment without ever opening the UI.

Ready to pilot your first test from your coding agent?

Get started with the MCP Server.
Your Gatling Enterprise Edition account is all you need.

Check your inbox We just sent the getting started guide to your email.

FAQ

Frequently Asked Questions about Gatling AI Extensions

Do I need a Gatling Enterprise Edition account?

Yes. Both components connect to Gatling Enterprise Edition via an API token. You need a valid account and a token with the Configure role.

Does my data leave my machine?

No. The MCP Server runs locally via stdio. All communication is between your machine and your Gatling Enterprise Edition account directly.

Which coding agents are supported?

The MCP Server works with any MCP-compatible client: Claude Code, Claude Desktop, Cursor, Windsurf, VS Code with Copilot. Skills are packaged as a Claude Code plugin today and can be adapted for
other agents.

Can my agent modify my infrastructure, or just read it?

Both. Beyond reading teams, packages, tests, runs, and locations, it can register source repositories, create and configure tests, and start or stop runs, scoped by your API token's role.