Browser Use Server

Instructions

Implementation Reference

• src/browser_handler.py:249-295 (handler)

  Main execution logic for get_console_logs: validates URL, runs AI agent for navigation and steps, injects JavaScript to override console methods and capture logs in window._consoleLogs, retrieves and returns the logs.

  elif command == 'get_console_logs':
      if not args.get('url'):
          return {
              'success': False,
              'error': 'URL is required for get_console_logs command'
          }
  
      console_messages = []
      def on_console_message(msg):
          console_messages.append(f"type: {msg.type}, text: {msg.text}, location: {msg.location}")
  
      task = f"1. Go to {args['url']}"
      if args.get('steps'):
          steps = args['steps'].split(',')
          for i, step in enumerate(steps, 2):
              task += f"\n{i}. {step.strip()}"
          task += f"\n{len(steps) + 2}. Get the console logs"
      else:
          task += f"\n2. Get the console logs"
      use_vision = os.getenv('USE_VISION', 'false').lower() == 'true'
      agent = Agent(task=task, llm=llm, use_vision=use_vision, browser_context=context)
      await agent.run()
  
      try:
          # Execute JavaScript to get console logs
          await context.execute_javascript("""
              window._consoleLogs = [];
              const originalConsole = window.console;
              ['log', 'info', 'warn', 'error'].forEach(level => {
                  window.console[level] = (...args) => {
                      window._consoleLogs.push({type: level, text: args.join(' ')});
                      originalConsole[level](...args);
                  };
              });
          """)
          
          # Wait a bit for any console logs to be captured
          await asyncio.sleep(1)
          
          # Get the captured logs
          logs = await context.execute_javascript("window._consoleLogs")
          return {
              'success': True,
              'logs': logs
          }
      finally:
          await context.close()

• src/index.ts:214-231 (schema)

  Defines the tool schema for 'get_console_logs', including input schema with required 'url' and optional 'steps'.

  {
    name: 'get_console_logs',
    description: 'Get the console logs of a webpage',
    inputSchema: {
      type: 'object',
      properties: {
        url: {
          type: 'string',
          description: 'The URL to navigate to',
        },
        steps: {
          type: 'string',
          description: 'Comma-separated actions or sentences describing steps to take after page load (e.g., "click #submit, scroll down" or "Fill the login form and submit")',
        },
      },
      required: ['url'],
    },
  },

• src/index.ts:149-233 (registration)

  Registers the 'get_console_logs' tool (among others) in the MCP server's ListTools response, making it discoverable.

  this.server.setRequestHandler(ListToolsRequestSchema, async () => ({
    tools: [
      {
        name: 'screenshot',
        description: 'Take a screenshot of a webpage',
        inputSchema: {
          type: 'object',
          properties: {
            url: {
              type: 'string',
              description: 'The URL to navigate to',
            },
            full_page: {
              type: 'boolean',
              description: 'Whether to capture the full page or just the viewport',
              default: false,
            },
            steps: {
              type: 'string',
              description: 'Comma-separated actions or sentences describing steps to take after page load (e.g., "click #submit, scroll down" or "Fill the login form and submit")',
            },
          },
          required: ['url'],
        },
      },
      {
        name: 'get_html',
        description: 'Get the HTML content of a webpage',
        inputSchema: {
          type: 'object',
          properties: {
            url: {
              type: 'string',
              description: 'The URL to navigate to',
            },
            steps: {
              type: 'string',
              description: 'Comma-separated actions or sentences describing steps to take after page load (e.g., "click #submit, scroll down" or "Fill the login form and submit")',
            },
          },
          required: ['url'],
        },
      },
      {
        name: 'execute_js',
        description: 'Execute JavaScript code on a webpage',
        inputSchema: {
          type: 'object',
          properties: {
            url: {
              type: 'string',
              description: 'The URL to navigate to',
            },
            script: {
              type: 'string',
              description: 'The JavaScript code to execute',
            },
            steps: {
              type: 'string',
              description: 'Comma-separated actions or sentences describing steps to take after page load (e.g., "click #submit, scroll down" or "Fill the login form and submit")',
            },
          },
          required: ['url', 'script'],
        },
      },
      {
        name: 'get_console_logs',
        description: 'Get the console logs of a webpage',
        inputSchema: {
          type: 'object',
          properties: {
            url: {
              type: 'string',
              description: 'The URL to navigate to',
            },
            steps: {
              type: 'string',
              description: 'Comma-separated actions or sentences describing steps to take after page load (e.g., "click #submit, scroll down" or "Fill the login form and submit")',
            },
          },
          required: ['url'],
        },
      },
    ],
  }));

• src/index.ts:291-300 (handler)

  MCP CallTool request handler formats and returns the console logs result from the Python backend as text content.

  } else if (request.params.name === 'get_console_logs') {
    return {
      content: [
        {
          type: 'text',
          text: JSON.stringify(result.logs, null, 2),
        },
      ],
    };
  } else {

• src/index.ts:236-236 (registration)

  Validates that 'get_console_logs' is an allowed tool name in the CallTool handler.

  const validCommands = ['screenshot', 'get_html', 'execute_js', 'get_console_logs'];