MCP Server

Maintained

MIT

MarkGrab MCP Server

Name: MarkGrab MCP Server
Author: io.github.ArkNill

io.github.ArkNill/markgrab

Repository Registry

What is the MarkGrab MCP server?

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

How to install MarkGrab

Copy-paste configuration for popular MCP clients.

transport: stdio

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

Claude Desktop

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

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

Cursor

~/.cursor/mcp.json

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

Windsurf

~/.codeium/windsurf/mcp_config.json

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

VS Code

.vscode/mcp.json

{
  "servers": {
    "markgrab": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "markgrab"
      ]
    }
  }
}

Claude Code

claude mcp add markgrab -- uvx markgrab

Related MCP servers

Docpick

Maintained

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

Apache-2.0

View repository →

Browsegrab

Maintained

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

MIT

View repository →

Diffgrab

Maintained

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

MIT

View repository →

Embgrep

Maintained

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

MIT

View repository →

FeedKit

Maintained

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

MIT

View repository →

Snapgrab

Maintained

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

MIT

View repository →