MarkGrab
MCP server by github.com/arknill/markgrab
Universal web content extraction — any URL to LLM-ready markdown. HTML, YouTube, PDF, DOCX.
About MarkGrab
MarkGrab is an MCP (Model Context Protocol) server published by arknill in the official MCP registry, listed under AI & ML on Loomal. Universal web content extraction — any URL to LLM-ready markdown. HTML, YouTube, PDF, DOCX.
It ships as a Python package on PyPI (markgrab), so any MCP client that can launch a local process can run it.
Development happens in the open at github.com/arknill/markgrab, where the project has earned 2 GitHub stars.
Use MarkGrab with your agent
claude mcp add markgrab -- uvx markgrab{
"mcpServers": {
"markgrab": {
"command": "uvx",
"args": [
"markgrab"
]
}
}
}markgrabFrequently asked questions
- What is MarkGrab?
- MarkGrab is an MCP (Model Context Protocol) server by arknill in the AI & ML category. Universal web content extraction — any URL to LLM-ready markdown. HTML, YouTube, PDF, DOCX.
- How do I connect MarkGrab to Claude, Cursor, or another MCP client?
- Install MarkGrab from its pypi package (markgrab) and register it under "mcpServers" in your client's MCP configuration — for example claude_desktop_config.json or Cursor's mcp.json — then restart the client.
- Is MarkGrab open source?
- Yes — the source code is public at github.com/arknill/markgrab, with 2 GitHub stars.
- Can AI agents pay to use MarkGrab?
- Not yet through Loomal — MarkGrab is listed as a free directory entry. If its maintainer verifies ownership, they can set per-call USDC pricing that agents pay over x402, with settlement on Base.
More AI & ML MCP servers
Apollo MCP Server
289
MCP server that exposes GraphQL operations as tools for AI models.
anki-mcp-server
242
MCP server enabling LLMs to interact with Anki flashcard software through AnkiConnect
MinerU Open MCP
118
Parse PDFs, images, doc, docx, ppt, pptx, xls, xlsx, html into Markdown using MinerU API.
time-mcp
66
Time MCP Server, giving LLMs time awareness capabilities.
aaa-mcp
45
Constitutional AI Governance with 13 enforced floors (F1-F13) and tri-witness consensus for LLMs.
selvage
34
An LLM-based code review MCP server with AST-powered smart context extraction
Listing data from the official MCP registry and GitHub, refreshed periodically. Not affiliated with the maintainer unless claimed. Maintain MarkGrab? Claim this listing free by verifying GitHub ownership, or contact us.