Back to search
30
MCP

Browsegrab

io.github.arknill/browsegrab

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

Uptime
0.0%
4 probes
Response
0ms
last probe
Tools
0
callable
Primary URL
—

Similar MCP servers embedding-nearest

MarkGrab
Universal web content extraction — any URL to LLM-ready markdown. HTML, YouTube, PDF, DOCX.
0 tools
TheCrawler
Universal web scraper with LLM-ready markdown, RAG chunking, PDF/DOCX support.
0 tools
io.github.bch1212/agentfetch
Token-budgeted web fetch for AI agents — auto-routes Jina, FireCrawl, Trafilatura, PDF.
0 tools
io.github.insideos-designs/cowork-qa
Goal-driven Playwright browser sessions for LLMs, with full action traces and aria-snapshots.
0 tools
acuvity/mcp-server-playwright
Browser automation for LLMs using structured accessibility snapshots.
0 tools
PageMap
Structured web intelligence for AI agents. 5x fewer tokens than Playwright/Firecrawl, 84.7% accuracy
0 tools

How to use

Add to your Claude Desktop / Cursor / Cline MCP config:

{
  "mcpServers": {
    "browsegrab": {
      "url": "None",
      "transport": "http"
    }
  }
}