{"uid":"cap_251T51JPme3iPH0ctHA6z","slug":"mcp-compiler-agentdiet-dev-rag-token-diet-bm25-budget-controlled-web-8ca6e7dd","name":"RAG Token Diet – BM25 Budget-Controlled Web Distiller","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-token-diet)","url":"https://mcp-compiler.agentdiet.dev/v1/rag-token-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_mnrr45liJVyZ7Rbg2f5JZ","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 and distills a URL or raw HTML into compressed Markdown, structured JSON, skeleton outlines, or BM25-focused excerpts within a strict token budget","exampleAgentPrompt":"Distill the content at https://docs.stripe.com/payments/accept-a-payment into clean Markdown using budget mode, focused on the query 'accept payment', and keep the output under 300 tokens so I don't blow my context window.","exampleUseCases":[{"title":"RAG pipeline token cost reduction","prompt":"Fetch https://en.wikipedia.org/wiki/Retrieval-augmented_generation and distill it in budget mode with the query 'how RAG works', capping the output at 400 tokens — I want just the most relevant passages without wasting context."},{"title":"Competitor pricing page extraction","prompt":"Grab the HTML from our competitor's pricing page at https://www.competitor.com/pricing and distill it into structured JSON tables so I can see their tiers and prices in a clean format."},{"title":"Documentation skeleton for navigation","prompt":"Pull https://docs.openai.com/api-reference and give me a skeleton outline of the page so I can understand the top-level structure without reading the full thing."}],"resultDescription":"Returns a JSON object with a 'data' field containing the distilled content (Markdown text, structured JSON, skeleton outline, or BM25-focused excerpt depending on mode), an 'roi_proof' object showing raw_tokens, distilled_tokens, tokens_saved, compression_ratio_pct, and llm_cost_saved_usd, plus optional cache hit/miss status and billing details.","failureModes":["URL is unreachable or returns non-200 HTTP status — endpoint may return an error status","HTML payload is empty or malformed — distillation may produce empty or low-quality output","max_tokens set too low (below 20) — rejected by schema validation","BM25 query provided without mode=budget — query may be ignored","Rate limit or payment failure via x402 — call blocked with 402 Payment Required","Idempotency key reused with different parameters — may return cached result from prior call"],"whenToPreferThis":"Choose this endpoint when you need to feed web content into an LLM pipeline but want to minimize token usage and cost. It is especially valuable in RAG workflows where only the most relevant passages (matched by BM25 query) are needed, or when you want structured JSON/skeleton output rather than raw HTML. Prefer it over generic scraping tools when token budget control and compression ROI metrics matter.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:31:04.261Z","isFirstParty":false,"canonicalSlug":"mcp-compiler-agentdiet-dev-rag-token-diet-bm25-budget-controlled-web-8ca6e7dd"}