{"uid":"cap_69he1njDUriiCYXsOpw_u","slug":"mcp-compiler-agentdiet-dev-web-distiller-with-bm25-budget-control-99b1319d","name":"Web Distiller 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/web-scrape)","url":"https://mcp-compiler.agentdiet.dev/v1/web-scrape?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_cCbuwzqVzGRKbKS1a3uXT","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 Markdown, structured data, skeleton, or BM25-focused excerpts within a strict token budget","exampleAgentPrompt":"Can you fetch https://stripe.com/docs/api/charges and distill it into clean Markdown, keeping it under 2000 tokens and focusing on the 'create a charge' section?","exampleUseCases":[{"title":"Token-budget API doc extraction","prompt":"Grab the OpenAI pricing page at https://openai.com/pricing and distill it down to under 1500 tokens using budget mode, focused on the query 'GPT-4 cost per token'."},{"title":"Competitive product page analysis","prompt":"Fetch https://www.notion.so/product and convert it into structured JSON tables and metadata so I can compare their feature list against competitors."},{"title":"Clean readable article from raw HTML","prompt":"I have this raw HTML blob from a news article — can you distill it into clean Markdown and tell me how many tokens you saved?"}],"resultDescription":"Returns a JSON object containing the distilled content (Markdown text, structured tables/metadata, skeleton outline, or BM25-focused excerpt depending on mode), along with ROI proof metrics (raw vs distilled token counts, compression ratio, estimated LLM cost saved), cache status (HIT/MISS), and billing details including fee charged.","failureModes":["Invalid or unreachable URL returns fetch error","Raw HTML too large may exceed processing limits","BM25 budget mode requires both query and max_tokens to be useful","Token budget set too low may produce empty or truncated output","Paywalled or JavaScript-heavy pages may not distill correctly","Payment failure via x402 returns 402 with payment instructions"],"whenToPreferThis":"Choose this endpoint when you need to convert a live webpage or raw HTML into LLM-ready content while controlling token cost. It is especially valuable when processing large documentation pages, competitive intelligence pages, or any HTML where only a semantically relevant subset is needed. The BM25 budget mode is uniquely suited for focused extraction when a specific query is known, and the ROI proof output makes it easy to quantify savings for cost-conscious agent pipelines.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:30:52.909Z","isFirstParty":false,"canonicalSlug":"mcp-compiler-agentdiet-dev-web-distiller-with-bm25-budget-control-99b1319d"}