{"uid":"cap_JP3CQVgwgW8xyDtNtGYR0","slug":"mcp-compiler-agentdiet-dev-article-extractor-with-bm25-budget-control-c02a5934","name":"Article Extractor 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/article-extractor)","url":"https://mcp-compiler.agentdiet.dev/v1/article-extractor?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_klhWW827Nyaj4y-Zc7GCY","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 webpage URL or raw HTML into clean Markdown, structured JSON, skeleton outline, or a BM25-ranked token-budget excerpt","exampleAgentPrompt":"Distill the article at https://techcrunch.com/2024/01/15/openai-news/ into clean Markdown, and if it's too long, use budget mode with the query 'OpenAI funding' and keep it under 500 tokens.","exampleUseCases":[{"title":"Token-budget webpage summary for LLM pipeline","prompt":"Fetch https://www.wired.com/story/ai-regulation-europe/ and distill it into Markdown, but keep the output under 800 tokens using budget mode focused on 'EU AI regulation'."},{"title":"Structured data extraction from product page","prompt":"Extract the content from https://stripe.com/docs/payments/payment-intents in structured mode so I can get the tables and metadata as JSON."},{"title":"Compress raw HTML for LLM cost savings","prompt":"I have a big blob of raw HTML from a news article — can you distill it into clean Markdown and tell me how many tokens it saved compared to the original?"}],"resultDescription":"Returns a distilled representation of the webpage in the requested mode (Markdown, structured JSON with tables/metadata, skeleton outline, or BM25-ranked token-budget excerpt), along with ROI proof showing raw vs. distilled token counts, compression ratio, tokens saved, and estimated LLM cost saved. Also includes cache hit/miss status and billing details.","failureModes":["URL unreachable or returns non-200 status — endpoint may return an error status","Malformed or empty HTML input — distillation fails with no content","Token budget too small (below minimum of 20) — validation error","BM25 query provided without mode=budget — query may be ignored","Rate limit or payment failure via x402 — request blocked","Page requires JavaScript rendering — static fetch may return incomplete content"],"whenToPreferThis":"Choose this endpoint when you need to reduce the token footprint of web content before passing it to an LLM, especially when you have a strict token budget or want to focus extraction on a specific query using BM25 ranking. It is superior to raw web scraping for LLM pipelines because it returns already-cleaned, compressed content with measurable ROI metrics. Use it over generic scrapers when you need multiple output modes (Markdown, structured JSON, skeleton, or budget excerpt) from a single endpoint.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:34:22.119Z","isFirstParty":false,"canonicalSlug":"mcp-compiler-agentdiet-dev-article-extractor-with-bm25-budget-control-c02a5934"}