playwright-browser-console-messages

To read console logs from the current page, retrieve console messages for debugging JavaScript output.

⭐6stars🔀3forks📁View on GitHub🕐Updated Jan 7, 2026⬇️1downloads

When & Why to Use This Skill

The playwright-browser-console-messages skill allows Claude to programmatically access and retrieve real-time console logs from a web browser. By capturing JavaScript output, including errors, warnings, and debug information, it empowers developers and automated agents to diagnose front-end issues, monitor script execution, and ensure web application stability during automated browsing sessions.

Use Cases

  • JavaScript Error Tracking: Automatically capture and analyze runtime exceptions and stack traces to identify why a webpage is failing to execute specific scripts.
  • Web Application Testing: Monitor console warnings and info logs during QA automation to ensure that new features don't trigger hidden regressions or performance alerts.
  • Client-Side Debugging: Filter and retrieve specific log levels (e.g., only 'error' or 'warning') to quickly isolate critical bugs in complex web interfaces without manual inspection.
  • Verification of Analytics and Events: Confirm that specific tracking pixels or event logs are being fired correctly by inspecting the console output during user flow simulations.
nameplaywright-browser-console-messages
description"To read console logs from the current page, retrieve console messages for debugging JavaScript output."

Usage

Use the MCP tool dev-swarm.request to send the payload as a JSON string:

{"server_id":"playwright","tool_name":"browser_console_messages","arguments":{}}

Tool Description

Returns all console messages

Arguments Schema

The schema below describes the arguments object in the request payload.

{
  "type": "object",
  "properties": {
    "level": {
      "type": "string",
      "enum": [
        "error",
        "warning",
        "info",
        "debug"
      ],
      "default": "info",
      "description": "Level of the console messages to return. Each level includes the messages of more severe levels. Defaults to \"info\"."
    }
  },
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}

Background Tasks

If the tool returns a task id, poll the task status via the MCP request tool:

{"server_id":"playwright","method":"tasks/status","params":{"task_id":"<task_id>"}}