The Debugg AI MCP Server is an AI-driven browser automation and end-to-end testing tool that offers:
Natural Language Testing: Run UI tests by describing features or flows in plain language
Local Application Support: Test web applications running on
localhostportsMCP Protocol Integration: Seamlessly connect with AI agents and MCP-compatible clients
Real-Time Updates: Receive step-by-step notifications during test execution
Visual Verification: Capture screenshots of the final page state
Zero Configuration: Eliminate the need for local browser or Playwright setup
CI/CD Compatibility: Access historical test results for pipeline integration
Secure Remote Execution: Use managed browsers via secure tunnels
Deployment Options: Quick setup via NPX or Docker for local and remote use
Provides Docker container deployment option for running the MCP server with configurable environment variables
Integrates with GitHub repositories for testing web applications, with support for specifying repo name and branch information
Compatible with LangChain agents as MCP clients for browser automation and end-to-end testing
Available as an npm package (@debugg-ai/debugg-ai-mcp) for easy installation and integration
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Debugg AI MCPtest the login flow on my app running on port 3000"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Official MCP Server for Debugg AI
AI-powered browser testing and monitoring via the Model Context Protocol (MCP). Gives AI agents the ability to run end-to-end browser tests, monitor live sessions, and validate UI changes against your running application.
What it does
Run browser tests with natural language — describe what to test, the AI agent clicks through your app and returns screenshots + results
Monitor live browser sessions — capture console logs, network requests, and screenshots in real time
Manage test suites — create, organize, and track E2E tests tied to features or commits
Seamless CI/CD — view all results in your Debugg.AI dashboard
Related MCP server: DevDb MCP Server
Demo
Prompt: "Test the ability to create an account and login"
Result:
Duration: 86.80 seconds
Status: Success — signed up and logged in with
alice.wonderland1234@example.com
Quick Setup
1. Get your API key
Create a free account at debugg.ai and generate your API key.
2. Add to Claude Desktop
{
"mcpServers": {
"debugg-ai": {
"command": "npx",
"args": ["-y", "@debugg-ai/debugg-ai-mcp"],
"env": {
"DEBUGGAI_API_KEY": "your_api_key_here"
}
}
}
}Or with Docker:
docker run -i --rm --init \
-e DEBUGGAI_API_KEY=your_api_key \
quinnosha/debugg-ai-mcpTools
E2E Testing
Tool | Description |
| Run a browser test with a natural language description. Returns screenshots and pass/fail result. |
| Generate a suite of browser tests for a feature or workflow |
| Auto-generate tests from recent git commits |
| Check progress and results of a running or completed test suite |
Test Management
Tool | Description |
| List all E2E tests with filtering and pagination |
| List all test suites |
| List all commit-based test suites |
Live Session Monitoring
Tool | Description |
| Launch a remote browser session with real-time monitoring |
| Stop an active session and save captured data |
| Check session status, current URL, and uptime |
| Retrieve console logs, network requests, and JS errors |
| Capture a screenshot of what the browser currently shows |
Quick Operations
Tool | Description |
| Capture a screenshot of any URL — no session setup required |
Configuration
# Required
DEBUGGAI_API_KEY=your_api_key
# Optional — provide defaults so you don't have to pass them every time
DEBUGGAI_LOCAL_PORT=3000 # Your app's local port
DEBUGGAI_LOCAL_REPO_NAME=your-org/repo # GitHub repo name
DEBUGGAI_LOCAL_REPO_PATH=/path/to/project # Absolute path to project root
DEBUGGAI_LOCAL_BRANCH_NAME=main # Current branch
# Override API endpoint (defaults to https://api.debugg.ai)
DEBUGGAI_API_URL=https://api.debugg.aiUsage examples
"Test the user login flow on my app running on port 3000"
"Check that the checkout process works end to end"
"Take a screenshot of localhost:3000 and tell me if anything looks broken"
"Create a test suite for the user authentication feature"
"Generate browser tests for my last 3 commits"Local Development
npm install
npm test
npm run build
# Test with MCP inspector
npx @modelcontextprotocol/inspector --config test-config.json --server debugg-aiLinks
Dashboard: app.debugg.ai
Docs: debugg.ai/docs
Issues: GitHub Issues
Discord: debugg.ai/discord
Apache-2.0 License © 2025 DebuggAI
Resources
Looking for Admin?
Admins can modify the Dockerfile, update the server description, and track usage metrics. If you are the server author, to access the admin panel.