Clean Markdown runs on your own machine — the client starts it, so there is no endpoint to ping. 36 installs a week from npm. Last commit 24 Jul 2026.
Any URL to clean, LLM-ready Markdown for RAG. Strips ads, nav, and boilerplate.
Today is the operative word: we check Clean Markdown every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
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 mcp add clean-markdown -- npx -y clean-markdown-mcp
{
"mcpServers": {
"clean-markdown": {
"args": [
"-y",
"clean-markdown-mcp"
],
"command": "npx"
}
}
}
[mcp_servers.clean-markdown]
command = "npx"
args = ["-y", "clean-markdown-mcp"]
{
"mcpServers": {
"clean-markdown": {
"args": [
"-y",
"clean-markdown-mcp"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"clean-markdown": {
"args": [
"-y",
"clean-markdown-mcp"
],
"command": "npx"
}
}
}
Fetch URLs and return clean Markdown for RAG — nav, ads and boilerplate stripped.
LLM-ready web search + instant answers + URL-to-clean-text fetch for agents and RAG.
Read-only local-first MCP server for private Markdown, PDF, and Tika-backed search on Windows.
Read-only local-first MCP server for private Markdown, PDF, and Tika-backed search on Windows.
Universal web scraper with LLM-ready markdown, RAG chunking, PDF/DOCX support.
Full-text Asian financial reports (China, Korea, Japan) as clean Markdown — 6 tools for RAG agents.
Extract PDFs to Markdown, RAG chunks and cited tables; publish tracked Doc Links with read stats.
BM25 search + tree navigation over markdown docs for AI agents. No embeddings, no LLM calls.
Answers built from our own checks of this server.