Connect to Katalon Studio MCP Server

Last updated: November 2026

This document shows you how to connect the Katalon Studio MCP server to your AI coding agent, such as GitHub Copilot CLI, Claude, Codex, VS Code, or Cursor. Your agent can then read and edit your Katalon Studio project with the AI model and tools you already use.

note

If you also have a Katalon Platform subscription, you can add Katalon True MCP server as well, for a complete end-to-end testing workflow.

Overview

Availability

The Katalon Studio MCP server is available for Katalon Studio Enterprise and trial users only.

Starting from version 11.1.0, you can use the Katalon Studio MCP server in two ways:

• Work alongside Katalon Studio: when you open a project in Katalon Studio, the MCP server starts automatically. You use Studio and your AI coding agent side by side. Closing Studio stops the server.
• Work without opening Katalon Studio: you run a command from the Katalon Studio package to start the MCP server without the GUI, and work with your project from your AI coding agent only. See Use the MCP server without opening Katalon Studio.

Both ways use the same server settings.

Configure the MCP server

The MCP server comes with these default settings:

• Port 33699
• No authentication
• All tools enabled

To change them:

1. In Katalon Studio, go to Settings > Katalon > Katalon Studio MCP.
2. Configure:
   • Port: choose an available port.
   • Required Authentication: select to generate a secure token. Your AI coding agent must send this token to connect.
   • Available Tools: all tools are on by default. To stop your agent from using certain tools, turn them off. Tools you turn off are hidden from both Katalon AI Assistant and your AI coding agent.
3. Click Apply and Close.

In the same page, Server Status shows whether the server is Running, and Connection Configuration shows the details to paste into your AI coding agent. Click Copy to copy them.

Use the MCP server without opening Katalon Studio

You can start the MCP server with a command that runs Katalon Studio in MCP server mode (-runMode=mcp), without opening the GUI. Katalon Studio generates this command for you, with your project path and server settings already filled in.

warning

Katalon Studio can't run in GUI mode and MCP server mode at the same time on the same package. Close Katalon Studio before you run the command, and stop the command before you open Katalon Studio again.

Step 1: Generate the command

1. In Settings > Katalon > Katalon Studio MCP, under Use MCP Server without opening Katalon Studio, click Generate Command.

2. In Start MCP Server via Command Line, click Copy.

   
   

   The command includes your Katalon API key (-apiKey). Keep it private, and don't share or commit it.

3. Close Katalon Studio.

Step 2: Run the command from the Katalon Studio package

Windows

1. Open Command Prompt (CMD) in the folder that contains katalon.exe.
2. Paste and run the command.

MacOS

1. Right-click the Katalon Studio app and select Show Package Contents. You see the Contents folder.
2. Right-click the Contents folder and select New Terminal at Folder.
3. Paste and run the command.

Keep the terminal open. The MCP server runs as long as the command is running.

note

Each MCP server is tied to one project. To switch projects, stop the command and run it again with the new project path.

Command parameters

The generated command already includes your settings. To change them without opening Katalon Studio, edit these parameters in the command:

Parameters	Description	Example
-noSplash	Run Katalon without launching the UI splash screen	-noSplash
-runMode=mcp	Start Katalon in MCP server mode	-runMode=mcp
-projectPath	Path to the Katalon project to load	-projectPath=/Users/<username>/Katalon Studio/MyProject/MyProject.prj
-apiKey	API key used to authenticate Katalon license	-apiKey=ed9a0******
-mcp.server.port	Port used to host the MCP server	-mcp.server.port=10245
-mcp.server.auth.enabled	Enable or disable authentication for the MCP server	-mcp.server.auth.enabled=true
-mcp.server.auth.token	Token used for authenticating MCP requests	-mcp.server.auth.token=2077******
-mcp.server.excluded.tools	Comma-separated list of MCP tools to exclude from exposure (no spaces between commas).	-mcp.server.excluded.tools="createBddFeatureFile,createCustomKeyword,createDynamicTestSuite"

Next, connect your AI coding agent.

Connect the MCP server to common AI coding agents

The following examples use the default settings: Katalon Studio is open with your project, the port is 33699, and authentication is off. The server URL is:

http://localhost:33699/mcp/stream

If you changed the port, turned on authentication, or started the server without opening Katalon Studio, adjust the URL and add your token where needed.

Select your coding agent:

GitHub Copilot CLI

Requirements

GitHub Copilot CLI is installed, and a copilot session is open.

Follow these steps:

1. Add the server. In the copilot session, type /mcp add and fill in the form. Press Tab to move between fields.

   • Server Name: katalon-studio
   • Server Type: HTTP
   • URL: http://localhost:33699/mcp/stream
   • HTTP Headers: leave empty.
   • Tools: *

   Press Ctrl+S to save. You don't need to restart GitHub Copilot CLI.

2. Check the connection. Type /mcp. You should see katalon-studio with tools such as listEntityFiles and writeTestCase.

3. Try a prompt, for example:

   List all test cases in this project.

   If GitHub Copilot CLI returns the test cases in your project, the connection works.

Claude

Follow these steps:

1. Create a .json file in the Claude folder:
   • For Windows: %APPDATA%\Claude\
   • For MacOS/Linux: ~/Library/Application Support/Claude/
2. Paste the following into the JSON file. Adjust to match your configuration:

{
  "mcpServers": {
    "my-server": {
      "command": "npx",
      "args": ["mcp-remote", "http://localhost:33699/mcp/stream"]
    }
  }
}

Codex

Add through the UI

1. Open Settings, and under Integrations, click Plugins.
2. Select the MCPs tab, then click + Add server.
3. Fill in the dialog:
   • Name: katalon-studio
   • Transport / Type: Streamable HTTP
   • URL: http://localhost:33699/mcp/stream
4. Click Save. The katalon-studio server appears in the list — make sure its toggle is on.

Edit config.toml directly

1. Open Settings > Configuration.

2. In Custom config.toml settings, keep the scope on User config (or choose a project scope), then click Open config.toml.

3. Add the server and save:

   [mcp_servers.katalon-studio]
   url = "http://localhost:33699/mcp/stream"

4. Restart Codex. This is the same ~/.codex/config.toml shared by the app/IDE and the CLI, so the server also shows up under Plugins > MCPs.

warning

The header must be [mcp_servers...] (with an underscore). mcp-servers or mcpservers will be silently ignored.

For older Codex versions without HTTP support, use the mcp-remote bridge instead:

[mcp_servers.katalon-studio]
command = "npx"
args = ["mcp-remote", "http://localhost:33699/mcp/stream"]

VS Code

To connect Katalon Studio MCP server to VS Code, create a mcp.json file and add the connection configuration:

{
  "servers" : {
  "katalon-studio" : {
  "type": "http",
  "url": "http://localhost:33699/mcp/stream"
    }
  }
}

For more details, see the VS Code Documentation.

Cursor

Follow these steps:

1. Copy the connection configuration from Katalon Studio.
2. Paste it into Cursor's MCP configuration.
3. Use Katalon AI Assistant and the tool in parallel.