Browsegrab MCP Server

io.github.ArkNill/browsegrab

What is the Browsegrab MCP server?

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

Copy-paste configuration for popular MCP clients.

transport: stdio

Config generated by PluginBench — verify against the source before use.

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "browsegrab": {
      "command": "uvx",
      "args": [
        "browsegrab"
      ]
    }
  }
}

Maintained

Web page change tracking with structured diffs. markgrab + snapgrab integration.

MIT

Maintained

Schema-driven document extraction with local OCR + LLM. Document in, Structured JSON out.

Apache-2.0

Maintained

Local semantic search — embedding-powered grep for files, zero external services.

MIT

Maintained

RSS/Atom feed collection with 417 curated feeds. Python MCP server.

MIT

Maintained

Universal web content extraction — any URL to LLM-ready markdown. HTML, YouTube, PDF, DOCX.

MIT

Maintained

URL to screenshot with metadata. Python MCP server. Claude Vision optimized.

MIT