Donobu MCP Server

This is a Model Context Protocol (MCP) server that acts as a bridge between an AI IDE (like Cursor or VS Code with Copilot) and the Donobu Studio application. It lets you test features of your application in a browser, while you (or your AI) are developing it, and can generate Donobu-powered Playwright tests based on successful test runs.

Tools Provided

test_website_feature_in_browser

Your LLM can use this tool to test the functionality of a website feature, whether new or in development, in a browser. Donobu Studio will create a new autonomous test run (or "flow") and start the execution of the test run.

check_test_run_status_and_results

Use this tool to get the status and (if completed) the results of a specific test run (or "flow"). Once the test run is complete, you will also have access to the complete test run video, or an image of the final state of the browser if no video is available. You can also look back at previous flows (or even watch the progress of the current one) in the Donobu Studio application.

create_test_file_for_test_run

Use this tool to generate a Donobu-powered Playwright test file after a successful test run, and add it to your project. The test file will contain the steps of the test run, and the expected results.

Prerequisites

• Donobu Studio desktop application. Make sure the application is running.

Setup

The easiest way to use this MCP server is via npx. Add this to your MCP configuration file:

{
  "mcpServers": {
    "donobu": {
      "command": "npx",
      "args": ["@donobu/mcp@latest"]
    }
  }
}

This will automatically download and run the latest version of the server without requiring manual installation or updates.

Configuration file locations vary slightly by MCP client. Most support both a home directory MCP configuration file, which will apply to all projects, and project-specific MCP configuration file. Here are the locations of each for some popular MCP clients:

Claude Code (CLI and VS Code extension)

• ~/.claude.json (in your home directory)
• .mcp.json (in a project directory)

Or just type this on the command line:

claude mcp add donobu -- npx @donobu/mcp@latest

Cursor

• ~/.cursor/mcp.json (in your home directory)
• .cursor/mcp.json (in a project directory)

Or just click on this link:

GitHub Copilot

• ~/.copilot/mcp-config.json (in your home directory)
• .vscode/mcp.json (in a project directory)

Codex

• ~/.codex/config.json (or ~/.codex/config.toml, but this will be a slightly different format)
• .mcp.json (in a project directory)