{"uid":"cap_SJCYhmf8vcppUr4q-Ng_3","slug":"mcp-compiler-agentdiet-dev-agentdiet-markdown-distill-bm25-budget-web-a8f3f7fd","name":"AgentDiet Markdown Distill — BM25 Budget 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/markdown-distill)","url":"https://mcp-compiler.agentdiet.dev/v1/markdown-distill?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_PZagiAcXAqzlsF-u_RZAI","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 compact, agent-ready Markdown, structured JSON, skeleton outline, or a BM25-focused token-budget excerpt","exampleAgentPrompt":"Distill https://stripe.com/docs/payments into compact markdown using budget mode, focused on the query 'payment intents', and keep it under 800 tokens.","exampleUseCases":[{"title":"Token-budget doc scraping for agent context","prompt":"Fetch https://docs.openai.com/api-reference and give me a BM25-focused excerpt about 'function calling' capped at 600 tokens — I need to fit it into my agent's context window."},{"title":"Clean markdown from noisy product page","prompt":"Take the HTML from this e-commerce product page I'm pasting and distill it into clean markdown — strip all the nav bars, ads, and boilerplate so I just get the product details."},{"title":"Skeleton outline of a long article","prompt":"Grab https://en.wikipedia.org/wiki/Transformer_(machine_learning_model) and give me a skeleton outline of the page structure so I can see what sections are covered without reading the whole thing."}],"resultDescription":"Returns a JSON object with a 'data' field containing the distilled content (Markdown text, structured JSON tables/metadata, skeleton outline, or BM25-ranked excerpt depending on mode), plus an 'roi_proof' object showing raw vs. distilled token counts, compression ratio, tokens saved, and estimated LLM cost saved in USD. Also includes cache hit/miss status and billing details.","failureModes":["URL is unreachable or returns non-200 status — service may return an error status","Raw HTML payload too large — may hit server-side size limits","mode=budget without a 'query' parameter — BM25 ranking has no focus signal","max_tokens set too low (below 20) — rejected by schema validation","Target page behind authentication/paywall — fetch returns login page instead of content","Payment not provided or insufficient — HTTP 402 response blocking execution"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to consume web content but must stay within strict token budgets, or when clean agent-ready Markdown is needed from noisy HTML pages. The BM25 budget mode is uniquely suited for precision retrieval from long documents — prefer it over generic scrapers when query-relevance-ranked compression matters. It is especially valuable when LLM cost reduction from web content is a priority, as the roi_proof response quantifies savings directly.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:23:43.423Z","isFirstParty":false,"canonicalSlug":"mcp-compiler-agentdiet-dev-agentdiet-markdown-distill-bm25-budget-web-a8f3f7fd"}