{"uid":"cap_N0yLXr2ftGiiF6b3N1Xpo","slug":"mcp-compiler-agentdiet-dev-agentdiet-web-distiller-compact-token-974c8a65","name":"AgentDiet Web Distiller — Compact Token Extraction from URLs","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":"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_oieBdiE6YjfJ3Xix5Rott","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 (or accepts raw HTML) and distills it into compact, agent-ready tokens using BM25 budget control and multiple extraction modes (markdown, structured, skeleton, or budget).","exampleAgentPrompt":"Distill https://stripe.com/docs/api into compact markdown tokens, keeping it under 2000 tokens using budget mode focused on the query 'payment intents'.","exampleUseCases":[{"title":"Token-budget research for agent pipeline","prompt":"Scrape https://openai.com/pricing and distill it into budget mode with a max of 1500 tokens, focused on the query 'API pricing tiers', so I can feed just the relevant part into my agent."},{"title":"Structured data extraction from a news article","prompt":"Fetch https://techcrunch.com/2024/01/15/some-article and extract it in structured mode so I get the tables, metadata, and key facts as JSON I can work with."},{"title":"Skeleton outline of a long documentation page","prompt":"Pull up https://docs.aws.amazon.com/ec2/index.html and give me a skeleton outline of the page so I can see its structure without wasting tokens on the full content."}],"resultDescription":"Returns a distilled version of the target webpage in the requested mode (markdown, structured JSON tables/metadata, skeleton outline, or BM25-focused budget excerpt), along with an ROI proof object showing raw vs. distilled token counts, compression ratio, tokens saved, and estimated LLM cost saved in USD. Also includes cache status and billing details.","failureModes":["URL is unreachable or returns a non-200 HTTP response — endpoint may return an error status","HTML too large or malformed — distillation may truncate or fail","mode=budget without a query or max_tokens — may default to full markdown without focusing","Payment (x402) not completed — returns HTTP 402 requiring USDC payment before proceeding","Invalid URL format — schema requires minLength 1 but malformed URLs may cause fetch errors","Rate limiting or timeout on slow external pages — latency spike or timeout error"],"whenToPreferThis":"Choose this endpoint when you need to feed web content to an LLM but want to minimize token consumption and cost. It is especially valuable when the target page is long and you only need a focused excerpt (use BM25 budget mode with a query), or when you want structured JSON tables/metadata rather than raw HTML. Prefer it over generic scraping tools when token compression ratios and LLM cost savings are a priority, or when you need the output in a directly agent-consumable format (markdown, skeleton outline, or structured JSON).","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T12:51:27.890Z","isFirstParty":false,"canonicalSlug":"mcp-compiler-agentdiet-dev-agentdiet-web-distiller-compact-token-974c8a65"}