dev.agentdiet/rag-diet

up checked 2026-11-11T05:37:31.791Z

Unclaimed · Unverified

Publisher-provided title

Imperium RAG-Diet — Web & Document Context Distiller (85-97% Token Savings)

Publisher-provided description

Strips 85-97% of HTML/DOM boilerplate into clean Markdown, skeletons, or BM25-ranked RAG chunks.

Summary by lookupd

Fetches web pages or raw HTML and returns cleaned Markdown, structured data, or compact section outlines for agent context.

Install

Claude Code, remote (streamable-http)

claude mcp add --transport http rag-diet https://rag-diet.agentdiet.dev/mcp

Codex, remote (streamable-http)

codex mcp add rag-diet --url https://rag-diet.agentdiet.dev/mcp

Cursor, remote (streamable-http) → .cursor/mcp.json

{
  "mcpServers": {
    "rag-diet": {
      "url": "https://rag-diet.agentdiet.dev/mcp"
    }
  }
}

Other clients: docs. Or tell your agent: Set up lookupd for me: read https://lookupd.com/agent.md and follow it.

Publisher-provided text

distill_webpage Fetch a public HTTP(S) web page (or accept raw HTML) and distill its main prose into clean Markdown, stripping 85-97% of HTML/JS/CSS boilerplate. WHEN TO USE: C
recon_webpage_skeleton Extract an ultra-compact structural outline (under ~200 tokens) of a web page listing its H1-H4 headings and exact token count per section without returning bod
extract_structured_data Extract machine-readable structured data from a web page: Schema.org JSON-LD objects, OpenGraph metadata, HTML tables parsed as JSON row arrays, fenced code blo
get_agent_wallet_status Inspect an agent's account ledger: remaining free trial calls (out of 5), prepaid USD balance, cumulative spend, total API calls, and total LLM tokens saved. WH

Shows this live status and links here; updates hourly.

[![lookupd status](https://lookupd.com/badge/dev.agentdiet/rag-diet.svg)](https://lookupd.com/servers/dev.agentdiet/rag-diet)