MarkGrab MCP
MarkGrab is a universal web content extraction tool that converts various URL types, including HTML, YouTube videos, PDFs, and DOCX files, into LLM-ready markdown. It features auto-detection of content types, async-first architecture using httpx and Playwright, and supports CLI and Python API usage for extracting clean text, titles, and metadata.
Package and access
Local package with source-attributed installation metadata. Koskamo does not execute packages during review.
What you can do with it
- Extract clean markdown from HTML articles
- Get YouTube video transcripts with timestamps
- Extract text and structure from PDF documents
- Parse DOCX files for paragraphs and headings
Source and maintenance
- Last repository push
- Maintenance checked
Packages and installation
Source-provided package data. Koskamo has not executed or live-probed this package.
markgrab 0.1.2
{
"version": "0.1.2",
"transport": "stdio",
"identifier": "markgrab",
"registryType": "pypi"
}Tools
Reported by the attributed source; not independently observed by Koskamo.
Maintenance history
Public check and source-refresh events. Editorial and ownership records remain private.
- · repository · passed · metadata changed · updated
- · backfill · recorded · Pre-expansion baseline; unobserved rich metadata remains unknown
Connect from your client
Each snippet configures the same source-provided package; replace placeholders before use.
Cursor
{
"mcpServers": {
"markgrab-mcp": {
"command": "uvx",
"args": [
"markgrab==0.1.2"
]
}
}
}Cline
{
"mcpServers": {
"markgrab-mcp": {
"command": "uvx",
"args": [
"markgrab==0.1.2"
]
}
}
}VS Code
{
"servers": {
"markgrab-mcp": {
"type": "stdio",
"command": "uvx",
"args": [
"markgrab==0.1.2"
]
}
}
}Claude Desktop
{
"mcpServers": {
"markgrab-mcp": {
"command": "uvx",
"args": [
"markgrab==0.1.2"
]
}
}
}Let your agent find its tools
Find servers like MarkGrab MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.