Refinery MCP runs on your own machine — the client starts it, so there is no endpoint to ping. 47 installs a week from npm. Last commit 28 Jun 2026.
Clean raw HTML into LLM-ready text before agents spend tokens.
Today is the operative word: we check Refinery MCP 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 refinery-mcp -- npx -y @larelabs/refinery-mcp
{
"mcpServers": {
"refinery-mcp": {
"args": [
"-y",
"@larelabs/refinery-mcp"
],
"command": "npx"
}
}
}
[mcp_servers.refinery-mcp]
command = "npx"
args = ["-y", "@larelabs/refinery-mcp"]
{
"mcpServers": {
"refinery-mcp": {
"args": [
"-y",
"@larelabs/refinery-mcp"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"refinery-mcp": {
"args": [
"-y",
"@larelabs/refinery-mcp"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
APIFY_TOKEN (Apify API token for the Refinery HTML cleaner actor).
The author declared them in the registry entry; get the values from the project itself.
LLM-ready web search + instant answers + URL-to-clean-text fetch for agents and RAG.
Cloud scraping & crawling API for AI agents. Turn any URL into clean, LLM-ready markdown.
Token-bounded repository context for coding agents over MCP.
Web page or HTML to clean LLM-ready Markdown or JSON. x402 pay-per-call, $0.005, no API key.
Token and context budget for AI agents. Tracks spend and gates the session.
Intelligent web content fetcher MCP server that converts HTML to clean, AI-readable JSONL format
Jina AI Reader/Search MCP — turn any URL into clean LLM-ready markdown, plus web search.
Read-only on-chain intelligence for AI agents on Base: balances, tokens, gas, tx status.
Answers built from our own checks of this server.