# Browser Lite

> Use this tool when you need to interact with a Chrome browser session locally and securely, providing direct control over tabs, page content, and JavaScript execution. It solves problems related to privacy and data security by keeping all data local and not routing it through cloud services. Browser Lite is ideal for use cases requiring secure and private automation of browser interactions, with inputs including authentication tokens and JavaScript code, and outputs such as accessibility trees and screenshots.

Canonical page: https://skillsregistry.net/skills/notoriouslab-browser-lite  
JSON: https://api.skillsregistry.net/v1/skills/notoriouslab-browser-lite

## Description

Browser Lite provides AI assistants with direct control over an existing Chrome browser session through a privacy-conscious local implementation. The server exposes four tools — listing open tabs, reading page content as an accessibility tree, capturing screenshots, and executing JavaScript — all running locally without routing data through cloud services. Authentication is provided via token-based security on both the MCP endpoint and WebSocket layers, and the accessibility tree output is 10-50x smaller than raw HTML while retaining semantic information.

## Trust

- **Trust score (0–1):** 0.63
- **Verification tier:** scanned
- **Last scanned:** 2026-09-02

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** browser-automation
- **Updated:** 2026-09-02

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/notoriouslab-browser-lite)
- **Repository:** <https://github.com/notoriouslab/browser-mcp-lite>

## 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": "notoriouslab-browser-lite"
    }
  }
}
```

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