{"uid":"cap_PvCM7yMM9Ad-l2kxBKcxc","slug":"mcp-compiler-agentdiet-dev-web-content-distiller-with-bm25-budget-aec4f2a3","name":"Web Content 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/context-compress)","url":"https://mcp-compiler.agentdiet.dev/v1/context-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_dzs5_Cab4KB9oKnvayHbU","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 compresses a URL or raw HTML into distilled Markdown, structured JSON, skeleton outline, or a BM25-ranked token-budget excerpt","exampleAgentPrompt":"Distill the content at https://stripe.com/docs/api into markdown, focus the BM25 ranking on 'payment intents', and keep it under 500 tokens so it fits in my context window.","exampleUseCases":[{"title":"LLM context-efficient webpage summarization","prompt":"Fetch https://openai.com/research/gpt-4 and compress it into clean markdown, keeping it under 800 tokens — I want just the key content without wasting my LLM context."},{"title":"Topic-focused BM25 excerpt from documentation","prompt":"Pull the Stripe API docs from https://stripe.com/docs/api and give me only the parts relevant to 'webhooks' using BM25 budget mode with a max of 300 tokens."},{"title":"Structured data extraction from raw HTML","prompt":"I have a raw HTML blob from a product page — distill it into structured JSON tables with pricing, metadata, and key fields extracted cleanly."}],"resultDescription":"Returns a 'data' object containing the distilled content (Markdown, structured JSON, skeleton outline, or BM25 excerpt depending on mode), plus ROI proof metrics showing raw vs. distilled token counts, tokens saved, compression ratio percentage, estimated LLM cost saved in USD, and a roi_multiplier. Also includes cache status (HIT/MISS) and billing details.","failureModes":["URL is unreachable or returns non-200 — fetch failure with error status","HTML payload is malformed or empty — distillation returns minimal/empty output","max_tokens set too low (below 20) — rejected by schema validation","BM25 query provided but mode is not 'budget' — query ignored or error","Payment not attached or insufficient — HTTP 402 payment required","Invalid mode enum value — schema validation error","Target URL blocks crawlers (robots.txt or JS-only rendering) — empty or partial content returned"],"whenToPreferThis":"Choose this endpoint when you need to reduce the token footprint of web content before passing it to an LLM, especially when working within strict context window limits. It is ideal for agent pipelines that fetch live documentation, news, or product pages and need a focused, compressed representation. The BM25 budget mode is uniquely valuable when you have a specific topic query and a hard token ceiling. Prefer this over generic scrapers when you also want ROI proof of compression savings and LLM cost reduction.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:34:01.355Z","isFirstParty":false,"canonicalSlug":"mcp-compiler-agentdiet-dev-web-content-distiller-with-bm25-budget-aec4f2a3"}