# AgentDiet RAG-Diet: BM25-Budgeted URL & HTML Distillation

> AgentDiet RAG-Diet: BM25-Budgeted URL & HTML Distillation is a paid API for AI agents from mcp-compiler.agentdiet.dev, paid per call via MPP, $0.001/call, status unknown (last checked 2026-10-23).

Fetches a URL or accepts raw HTML and distills it to compressed Markdown, structured JSON, skeleton outline, or a BM25-focused token-budget excerpt

## Facts

- Endpoint: POST https://mcp-compiler.agentdiet.dev/v1/rag-diet?utm_source=zero.xyz
- Price: $0.001/call
- Payment: MPP
- Status: unknown
- Last checked: 2026-10-23
- Activations on Zero: 0
- Provider: mcp-compiler.agentdiet.dev
- Website: https://mcp-compiler.agentdiet.dev
- Canonical page: https://www.zero.xyz/c/mcp-compiler-agentdiet-dev-agentdiet-rag-diet-bm25-budgeted-url-html-6f7228db
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_3wZkBlaVewBDX8WfoldOc

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability mcp-compiler-agentdiet-dev-agentdiet-rag-diet-bm25-budgeted-url-html-6f7228db -d '<json body>'
```

Example prompt: Distill https://stripe.com/docs/payments/checkout into compressed markdown using budget mode, focused on the query 'payment session creation', keeping it under 500 tokens.

## When to prefer this

Choose this endpoint when you need to reduce the token footprint of web content before feeding it into an LLM pipeline — especially when you want BM25-ranked relevance filtering against a specific query and a hard token ceiling. It is preferable over generic scrapers when you need both compression metrics (ROI proof) and multiple output modes (markdown, structured, skeleton, budget) from a single call. Use it for RAG ingestion, competitive intelligence, or any workflow where raw HTML is too large to include in a prompt directly.

## Known failure modes

- URL unreachable or returns non-200: fetch fails, distillation cannot proceed
- HTML payload too large or malformed: parsing may fail or produce poor output
- max_tokens set too low (below 20) for meaningful content: rejected by schema validation
- BM25 query provided without mode=budget: query parameter silently ignored
- Target site blocks crawlers: empty or blocked response returned
- Invalid URL format: request fails validation before fetch
- Rate limit or payment failure via x402: 402 response, no distillation performed

## How this service works

Distill a URL or raw HTML payload with BM25 budget control (Live x402 v2, IETF MPP & MCP endpoint at https://mcp-compiler.agentdiet.dev/v1/rag-diet)

## Output

Returns a JSON object with a 'data' field containing the distilled content (Markdown text, structured JSON tables/metadata, skeleton outline, or BM25-focused excerpt depending on mode), plus an 'roi_proof' object showing raw vs distilled token counts, compression ratio, tokens saved, and estimated LLM cost saved in USD. Optionally includes billing info and cache hit/miss status with latency.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "required": [
  "url"
 ],
 "properties": {
  "url": {
   "type": "string",
   "minLength": 1,
   "description": "Target webpage URL to fetch and distill (or builtin://stripe-docs)"
  },
  "html": {
   "type": "string",
   "description": "Optional raw HTML string to distill directly without fetching"
  },
  "mode": {
   "enum": [
    "markdown",
    "structured",
    "skeleton",
    "budget"
   ],
   "type": "string",
   "default": "markdown",
   "description": "Distillation mode"
  },
  "query": {
   "type": "string",
   "description": "BM25 focus query when mode=budget"
  },
  "max_tokens": {
   "type": "integer",
   "minimum": 20,
   "description": "Strict token budget ceiling when mode=budget"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "object",
 "required": [
  "status",
  "roi_proof",
  "data"
 ],
 "properties": {
  "data": {
   "type": "object",
   "description": "Distilled Markdown, structured JSON tables/metadata, skeleton outline, or BM25 budget excerpt."
  },
  "cache": {
   "type": "object",
   "properties": {
    "status": {
     "enum": [
      "HIT",
      "MISS"
     ],
     "type": "string"
    },
    "cache_key": {
     "type": "string"
    },
    "latency_ms": {
     "type": "number"
    }
   }
  },
  "status": {
   "type": "string",
   "description": "Execution status ('ok')"
  },
  "billing": {
   "type": "object",
   "properties": {
    "agent_id": {
     "type": "string"
    },
    "payment_method": {
     "type": "string"
    },
    "fee_charged_usd": {
     "type": "number"
    }
   }
  },
  "roi_proof": {
   "type": "object",
   "properties": {
    "raw_tokens": {
     "type": "integer"
    },
    "tokens_saved": {
     "type": "integer"
    },
    "roi_multiplier": {
     "type": "number"
    },
    "distilled_tokens": {
     "type": "integer"
    },
    "llm_cost_saved_usd": {
     "type": "number"
    },
    "compression_ratio_pct": {
     "type": "number"
    }
   }
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/mcp-compiler-agentdiet-dev-agentdiet-rag-diet-bm25-budgeted-url-html-6f7228db/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from mcp-compiler.agentdiet.dev](https://www.zero.xyz/host/mcp-compiler.agentdiet.dev/llms.txt)