Browsegrab
io.github.ArkNill/browsegrab
Token-efficient browser agent for local LLMs. Playwright + accessibility tree + MarkGrab.
Connect this server
Add this to your MCP client config — claude_desktop_config.json (Claude Desktop) or .cursor/mcp.json (Cursor).Suits: Claude Desktop · Cursor.
{
"mcpServers": {
"browsegrab": {
"command": "uvx",
"args": [
"browsegrab"
]
}
}
}A starting point — check the repository for exact arguments and setup. Restart your client after editing the config.
- Category
- Developer Tools
- Version
- 0.1.1
- Registry
- active
- Published
- 3/18/2026
More Developer Tools servers
Browse all Developer Tools →Diffgrab
QuartzUnit
Web page change tracking with structured diffs. markgrab + snapgrab integration.
Docpick
QuartzUnit
Schema-driven document extraction with local OCR + LLM. Document in, Structured JSON out.
Embgrep
QuartzUnit
Local semantic search — embedding-powered grep for files, zero external services.
FeedKit
QuartzUnit
RSS/Atom feed collection with 417 curated feeds. Python MCP server.
MarkGrab
QuartzUnit
Universal web content extraction — any URL to LLM-ready markdown. HTML, YouTube, PDF, DOCX.
Snapgrab
QuartzUnit
URL to screenshot with metadata. Python MCP server. Claude Vision optimized.
Add the badge to your site
Show visitors that Browsegrab is listed here — it’s also the link we check for a free listing.
HTML — for your website
<a href="https://serverdex.io/server/io-github-arknill-browsegrab?utm_source=badge"><img src="https://serverdex.io/brand/badge.svg" alt="Browsegrab — listed on Serverdex" width="123" height="40" loading="lazy"></a>Recommended. A dofollow link from your own domain is the one that counts for search engines, and it's the link we check for a free listing.
Markdown — for your README
[](https://serverdex.io/server/io-github-arknill-browsegrab?utm_source=badge)Nice for visibility, but GitHub marks README links nofollow, so it doesn't pass authority. Use the HTML badge on your site as well.