{"uid":"cap_o7St7aK03wiqQpM4P1wX1","slug":"mcp-compiler-agentdiet-dev-web-url-distiller-with-bm25-budget-control-7ec5796c","name":"Web URL 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/pdf-extract)","url":"https://mcp-compiler.agentdiet.dev/v1/pdf-extract?utm_source=zero.xyz","method":"GET","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_9yvfs6OYrSVENirV-j7cn","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 webpage URL (or accepts raw HTML) and compresses it into compact, agent-ready tokens using configurable distillation modes including BM25-focused budget extraction","exampleAgentPrompt":"Fetch https://stripe.com/docs/payments and distill it into compact markdown, keeping it under 2000 tokens using budget mode focused on the query 'payment intents API'.","exampleUseCases":[{"title":"Cost-efficient doc ingestion for agent","prompt":"Pull in the Stripe documentation at https://stripe.com/docs/api and compress it into structured markdown under 3000 tokens — I want to save on LLM costs when my agent reads it."},{"title":"Focused research extraction from article","prompt":"Go to https://techcrunch.com/2024/05/01/openai-latest/ and extract only the parts relevant to 'OpenAI funding' in budget mode with a max of 1500 tokens."},{"title":"Skeleton outline of competitor landing page","prompt":"Fetch https://www.competitor.com and give me a skeleton outline of their page structure so I can quickly understand how they've organized their content."}],"resultDescription":"Returns a 'data' object containing the distilled content (Markdown, structured JSON tables/metadata, skeleton outline, or BM25-focused excerpt depending on mode), plus an 'roi_proof' object showing raw vs. distilled token counts, tokens saved, compression ratio percentage, and estimated LLM cost saved in USD. Also includes cache hit/miss status and billing details.","failureModes":["Invalid or unreachable URL returns an error status","max_tokens below minimum of 20 is rejected","BM25 query mode without a query parameter may return unfiltered content","Raw HTML too large may be truncated or fail","Network timeouts on slow or blocked target pages","Payment/402 authentication failure prevents access"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to ingest web content efficiently without blowing the LLM context window — especially when you want BM25-guided token budgeting to focus on a specific query topic. Ideal for cost-conscious pipelines that repeatedly fetch documentation pages, news articles, or competitor content and need measurable compression ROI. Prefer over generic scrapers when you need markdown/structured/skeleton output modes and explicit token ceiling control.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:21:49.827Z","isFirstParty":false,"canonicalSlug":"mcp-compiler-agentdiet-dev-web-url-distiller-with-bm25-budget-control-7ec5796c"}