# mcp-browser

> mcp-browser — brainfuel-mcp-browser. Use this tool when you need to automate web browsing on macOS, driving a real WKWebView to solve problems like web scraping, automation testing, or interacting with web applications. It takes inputs like URLs, JavaScript commands, and user interactions, and outputs results like webpage content, cookies, and network requests. Ideal for use cases requiring native macOS web browsing capabilities, such as testing or automating web-based workflows.

Canonical page: https://skillsregistry.net/skills/brainfuel-mcp-browser  
JSON: https://api.skillsregistry.net/v1/skills/brainfuel-mcp-browser

## Description

Native macOS browser exposed as an MCP server — agents drive a real WKWebView.

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Category:** browser-automation
- **Updated:** 2026-09-21

## Source

- **Source listing:** [GitHub](https://github.com/brainfuel/mcp-browser)

## 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": "brainfuel-mcp-browser"
    }
  }
}
```

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