# Browser Tools

> Use this tool when you need to debug web applications, analyze performance issues, or improve site accessibility without leaving the AI conversation interface. It provides real-time access to console logs, network requests, screenshots, and DOM elements, and offers Lighthouse-powered audits for accessibility, performance, SEO, and best practices. The tool accepts web page URLs and browser interactions as inputs and outputs detailed reports and live updates through a WebSocket-enabled interface.

Canonical page: https://skillsregistry.net/skills/agentdeskai-browser-tools123  
JSON: https://api.skillsregistry.net/v1/skills/agentdeskai-browser-tools123

## Description

Browser Tools MCP provides a bridge between AI assistants and web browsers, enabling real-time access to console logs, network requests, screenshots, and DOM elements through a Chrome extension and server architecture. The implementation includes Lighthouse-powered audit capabilities for accessibility, performance, SEO, and best practices, with AI-optimized reporting that prioritizes critical issues. Built by AgentDesk AI, it uses WebSocket communication for live updates and includes a Puppeteer service for cross-platform browser automation, making it valuable for debugging web applications, analyzing performance issues, and improving site accessibility without leaving the AI conversation interface.

## Trust

- **Trust score (0–1):** 0.67
- **Verification tier:** scanned
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** browser-automation
- **Updated:** 2026-09-28

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/agentdeskai-browser-tools123)
- **Repository:** <https://github.com/weotzi/browser-tools-mcp>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "agentdeskai-browser-tools123"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/agentdeskai-browser-tools123` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/agentdeskai-browser-tools123/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt