Debugg AI MCP Server

What does “Debugg AI” MCP Server do?

The Debugg AI MCP Server is an AI-driven browser automation and end-to-end (E2E) testing server built around the Model Context Protocol (MCP). It enables AI assistants and agents to automate UI testing, simulate user behavior, and analyze the visual output of running web applications using natural language commands or CLI tools. This server eliminates the need for manual setup of testing frameworks like Playwright or browser proxies, offering a fully remote, managed solution that integrates seamlessly with local or remote development environments via secure tunnels. Developers can trigger UI tests based on user stories, track historical results, and incorporate these workflows into CI/CD pipelines, enhancing productivity and reliability in software development.

List of Prompts

No information about prompt templates is provided in the repository.

List of Resources

No explicit resources are listed in the repository.

List of Tools

• debugg_ai_test_page_changes
  Enables triggering UI tests based on user stories or natural language descriptions. This tool automates browser actions and E2E test flows, reporting progress and results back to the user.

Use Cases of this MCP Server

• Automated UI Testing
  Instantly run end-to-end UI tests on web applications using natural language descriptions, reducing the need for manual test scripting.
• Localhost Web App Integration
  Test development applications running on any localhost port, simulating real user interactions and flows without additional configuration.
• Continuous Integration/Continuous Deployment (CI/CD)
  Integrate automated E2E testing into CI/CD pipelines, ensuring new code changes are validated before deployment.
• Visual Output Analysis
  Analyze visual changes and UI regressions automatically as part of the testing workflow.
• Historical Test Tracking
  Access and review all previous test results in the Debugg.AI dashboard for audit and improvement.

How to set it up

Windsurf

1. Ensure prerequisites like Node.js are installed.
2. Open your Windsurf configuration file.
3. Add the Debugg AI MCP server to your list of MCP servers using the following JSON snippet:

   {
     "mcpServers": {
       "debugg-ai-mcp": {
         "command": "npx",
         "args": ["@debugg-ai/mcp-server@latest"]
       }
     }
   }
   

4. Save the configuration and restart Windsurf.
5. Verify that the server is running and accessible.

Claude

1. Install Node.js if not already present.
2. Locate Claude’s MCP configuration section.
3. Add the Debugg AI MCP server:

   {
     "mcpServers": {
       "debugg-ai-mcp": {
         "command": "npx",
         "args": ["@debugg-ai/mcp-server@latest"]
       }
     }
   }
   

4. Save changes and restart Claude.
5. Confirm server integration by checking for available MCP tools.

Cursor

1. Set up Node.js on your system.
2. Edit the Cursor MCP configuration file.
3. Insert the server entry:

   {
     "mcpServers": {
       "debugg-ai-mcp": {
         "command": "npx",
         "args": ["@debugg-ai/mcp-server@latest"]
       }
     }
   }
   

4. Save and reload Cursor.
5. Check the tool registry for the Debugg AI server tools.

Cline

1. Make sure Node.js is installed.
2. Open Cline’s MCP configuration file.
3. Add the following configuration:

   {
     "mcpServers": {
       "debugg-ai-mcp": {
         "command": "npx",
         "args": ["@debugg-ai/mcp-server@latest"]
       }
     }
   }
   

4. Save the file and restart Cline.
5. Validate the server’s availability.

Securing API Keys

To secure your API keys, use environment variables in your configuration:

{
  "mcpServers": {
    "debugg-ai-mcp": {
      "command": "npx",
      "args": ["@debugg-ai/mcp-server@latest"],
      "env": {
        "DEBUGG_AI_API_KEY": "${DEBUGG_AI_API_KEY}"
      },
      "inputs": {
        "apiKey": "${DEBUGG_AI_API_KEY}"
      }
    }
  }
}

How to use this MCP inside flows

Using MCP in FlowHunt

To integrate MCP servers into your FlowHunt workflow, start by adding the MCP component to your flow and connecting it to your AI agent:

Click on the MCP component to open the configuration panel. In the system MCP configuration section, insert your MCP server details using this JSON format:

{
  "debugg-ai-mcp": {
    "transport": "streamable_http",
    "url": "https://yourmcpserver.example/pathtothemcp/url"
  }
}

Once configured, the AI agent is now able to use this MCP as a tool with access to all its functions and capabilities. Remember to change “debugg-ai-mcp” to the actual name and replace the URL with your own MCP server URL.

Overview

A solid MCP server for AI-driven E2E testing, but the lack of documented prompt templates and explicit resources limits its extensibility for advanced MCP-based workflows. Tooling and setup are straightforward, and it covers the essential automation use cases. Rating: 6/10.

MCP Score