MarkGrab MCP Server

by arknill Your server? Claim it

local only

MarkGrab runs on your own machine — the client starts it, so there is no endpoint to ping. 122 installs a week from pypi. Last commit 15 Apr 2026.

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

Installs per day peak 42 · avg 21 · -10% w/w

a month agotoday

122

Installs / week

pypi · markgrab

Stars

0 open issues

15 Apr 2026

Last commit

from GitHub

MIT

License

Python

Nothing serious here today

Today is the operative word: we check MarkGrab every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

Connect this server

This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add markgrab -- uvx markgrab

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

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

~/.codex/config.toml

[mcp_servers.markgrab]
command = "uvx"
args = ["markgrab"]

.cursor/mcp.json

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

.vscode/mcp.json

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

Alternatives to MarkGrab

same job, measured the same way

TheCrawler

by manchittlab

Universal web scraper with LLM-ready markdown, RAG chunking, PDF/DOCX support.

69 installs/wk local only

Rendex: Rendering API for Images, PDFs & Content Extraction

by copperline-labs

Render HTML, Markdown, or URLs to images, PDF, or branded artifacts; extract and watch pages.

108 installs/wk 13 tools answering

MCP Document Converter

by xt765

Convert PDF, DOCX, HTML, Markdown, and Text for AI assistant context injection.

148 installs/wk local only

Hushvert

by hushvert

File conversion for AI agents: office docs, PDF to Word, video, and LLM-ready markdown via API.

54 installs/wk local only

Mdmagic MCP Server

by mdmagic-mcp

Use your own Word templates to convert Markdown → DOCX/PDF/HTML from any MCP-compatible AI.

87 installs/wk 10 tools answering

PDF to Text & Markdown with OCR

by monietools

PDF, DOCX and image URLs to clean, LLM-ready Markdown or text, with OCR for scanned pages.

answering

Distill MCP

by lakshgk

Convert PDF, DOCX, XLSX, PPTX, HTML, audio to token-efficient Markdown for any MCP client.

46 installs/wk local only

Brainiall Documents

by brainiall

High-fidelity PDF to structured Markdown conversion and document field extraction.

3 tools answering

MarkGrab — questions

Answers built from our own checks of this server.

Why is there no uptime for MarkGrab?

MarkGrab runs on your own machine over stdio — there is no network address to reach, so uptime cannot be measured for it by anyone. What can be measured is adoption: the pypi package markgrab was installed 122 times last week.

How do I connect MarkGrab?

Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It runs locally, so the command pulls markgrab straight from pypi; nothing to host, nothing to sign up for.

How many people use MarkGrab?

The pypi package markgrab was installed 122 times in the last week. Week over week that is -10%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.

Is MarkGrab open source?

Yes — it is published under the MIT licence, written in Python and 0 stars on GitHub. The source link is on this page, so you can read exactly what it does with your data before you connect it.