Lean Reader runs on your own machine — the client starts it, so there is no endpoint to ping. 59 installs a week from npm. Last commit 24 Jun 2026.
Token-minimized URL-to-clean-text reader for LLMs, with a token-savings receipt.
Today is the operative word: we check Lean Reader 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 lean-reader -- npx -y lean-reader
{
"mcpServers": {
"lean-reader": {
"command": "npx",
"args": [
"-y",
"lean-reader"
]
}
}
}
[mcp_servers.lean-reader]
command = "npx"
args = ["-y", "lean-reader"]
{
"mcpServers": {
"lean-reader": {
"command": "npx",
"args": [
"-y",
"lean-reader"
]
}
}
}
{
"servers": {
"lean-reader": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"lean-reader"
]
}
}
}
PDF, DOCX and image URLs to clean, LLM-ready Markdown or text, with OCR for scanned pages.
Token-optimized HTTP client for LLMs: fetches any URL as clean markdown. CLI and MCP server.
Focused repository context for Claude Code and Codex, with per-session token usage receipts.
LLM-ready web search + instant answers + URL-to-clean-text fetch for agents and RAG.
URL to clean markdown for LLMs: a polite, robots.txt-respecting web reader. Free, no API key
Mine your AI coding session logs into a you.md profile with dated receipts, for an agent to read.
Fetch public web pages as clean, token-budgeted text for AI agents.
Turn any web page URL or HTML into clean Markdown or plain text for an LLM to read.
Answers built from our own checks of this server.