{"uid":"cap_FC0YYRlnhOS3Ll2wjnYpx","slug":"mcp-compiler-agentdiet-dev-distill-url-or-html-with-bm25-budget-control-67e41831","name":"Distill URL or HTML with BM25 Budget Control","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/prompt-compress)","url":"https://mcp-compiler.agentdiet.dev/v1/prompt-compress?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_SOdelam27gqjXeYp0DCE5","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 into compressed Markdown, structured JSON, skeleton outline, or a BM25-ranked token-budget excerpt","exampleAgentPrompt":"Distill https://stripe.com/docs/payments/accept-a-payment into a BM25 budget excerpt focused on 'webhook events', keeping it under 500 tokens, so I can feed just the relevant parts to my LLM.","exampleUseCases":[{"title":"Token-budget Stripe docs extraction","prompt":"Pull the Stripe docs page at https://stripe.com/docs/api/charges and give me a BM25 excerpt focused on 'refund handling' with a strict ceiling of 300 tokens — I need to pass just the relevant section to my model."},{"title":"Clean Markdown from competitor landing page","prompt":"Fetch https://openai.com/pricing and distill it into clean Markdown, stripping all the nav and footer noise — I want the pricing table content only."},{"title":"Skeleton outline of a long article","prompt":"Take this raw HTML I'm pasting and return a skeleton outline of its structure — headings, subheadings, and key section labels — so I can decide which parts to dig into: <html>...</html>"}],"resultDescription":"Returns a JSON object with a 'data' field containing the distilled content (Markdown string, structured JSON tables/metadata, skeleton outline, or BM25-ranked excerpt depending on mode), plus an 'roi_proof' object showing raw_tokens, distilled_tokens, tokens_saved, compression_ratio_pct, roi_multiplier, and llm_cost_saved_usd, along with optional cache hit/miss status and billing details.","failureModes":["URL is unreachable or returns non-200 — endpoint may error or return empty distillation","HTML payload is malformed or empty — distillation may produce minimal output","mode=budget used without a query field — BM25 ranking cannot focus without a query","max_tokens set below 20 — rejected by schema validation","Target page is behind authentication or a CAPTCHA wall — fetch fails silently","Very large HTML payloads may exceed processing limits and return truncated results"],"whenToPreferThis":"Choose this endpoint when you need to feed web content into an LLM but must control token usage — especially when the target page is large, noisy, or contains boilerplate. The BM25 budget mode is uniquely suited for extracting only the most query-relevant sentences under a hard token ceiling, making it superior to generic scrapers when cost and context-window efficiency matter. Prefer it over raw fetch-and-pass approaches whenever you want compression ratio metrics and ROI proof alongside the distilled content.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:31:23.456Z","isFirstParty":false,"canonicalSlug":"mcp-compiler-agentdiet-dev-distill-url-or-html-with-bm25-budget-control-67e41831"}