{"uid":"cap_3wZkBlaVewBDX8WfoldOc","slug":"mcp-compiler-agentdiet-dev-agentdiet-rag-diet-bm25-budgeted-url-html-6f7228db","name":"AgentDiet RAG-Diet: BM25-Budgeted URL & HTML Distillation","description":"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)","url":"https://mcp-compiler.agentdiet.dev/v1/rag-diet?utm_source=zero.xyz","method":"POST","headers":{},"bodySchema":{"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"}}},"responseSchema":{"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"}}}}},"example":null,"exampleRequest":null,"tags":[],"displayCostAmount":"0.001","displayCostAsset":"USD","priceDynamic":false,"priceHint":null,"priceStatus":"priced","priceSource":"probe","requiresHandshake":false,"reviewCount":0,"rating":{"score":"0.00","successRate":"0.00","reviews":0,"stars":null,"state":"unrated"},"availabilityStatus":"unknown","priceObserved":null,"sessionDeposit":null,"pricing":{"kind":"static","summary":"$0.001/call","primary":{"kind":"static","protocol":"mpp","network":"tempo","amountUsd":"0.001","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"mpp","network":"tempo","amountUsd":"0.001","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_5c6uEGs_C4slPtxeVCKOW","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"mcp-compiler.agentdiet.dev","brandSlug":"mcp-compiler-agentdiet-dev-mpp","brandBaseUrl":"https://mcp-compiler.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches a URL or accepts raw HTML and distills it to compressed Markdown, structured JSON, skeleton outline, or a BM25-focused token-budget excerpt","exampleAgentPrompt":"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.","exampleUseCases":[{"title":"RAG pipeline webpage ingestion","prompt":"Fetch and distill https://docs.openai.com/api-reference into structured JSON tables so I can load it into my vector database without blowing my token budget."},{"title":"On-demand competitive page summarization","prompt":"Pull https://www.anthropic.com/product and give me a skeleton outline of their product page — I just need the section headings and key bullet points."},{"title":"Query-focused content extraction","prompt":"I have this raw HTML from a financial report — distill it in budget mode with the query 'revenue growth 2024' and cap it at 300 tokens so I can fit it into my prompt."}],"resultDescription":"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.","failureModes":["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"],"whenToPreferThis":"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.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:32:24.160Z","isFirstParty":false,"canonicalSlug":"mcp-compiler-agentdiet-dev-agentdiet-rag-diet-bm25-budgeted-url-html-6f7228db"}