# Browsegrab

> Use this tool when you need to efficiently browse and extract information from web pages for local Large Language Models (LLMs). Browsegrab solves problems related to web scraping, accessibility, and token-efficient data extraction, providing a robust interface for inputs such as URLs and outputs like structured data. It is ideal for use cases requiring automated web browsing and data extraction in resource-constrained environments.

Canonical page: https://skillsregistry.net/skills/io-github-arknill-browsegrab  
JSON: https://api.skillsregistry.net/v1/skills/io-github-arknill-browsegrab

## Description

Token-efficient browser agent for local LLMs. Playwright + accessibility tree + MarkGrab.

## Trust

- **Trust score (0–1):** 0.81
- **Verification tier:** verified
- **Last scanned:** 2026-08-28

## Facts

- **Version:** 0.1.1
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** browser-automation
- **Updated:** 2026-08-28

## Source

- **Source listing:** [MCP Registry](https://registry.modelcontextprotocol.io/v0/servers/io.github.ArkNill%2Fbrowsegrab)
- **Repository:** <https://github.com/QuartzUnit/browsegrab>

## 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": "io-github-arknill-browsegrab"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/io-github-arknill-browsegrab` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/io-github-arknill-browsegrab/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