{"uid":"cap_W6IT4mHseK_zrc4Nm3pcd","slug":"mcp-compiler-agentdiet-dev-agentdiet-token-optimizer-url-html-939d5800","name":"AgentDiet Token Optimizer – URL & HTML 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/token-optimizer)","url":"https://mcp-compiler.agentdiet.dev/v1/token-optimizer?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_Ibxw-vu2zZvHoMX0Arvm-","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 URL or raw HTML payload into compressed Markdown, structured JSON, skeleton outlines, or BM25-focused budget excerpts to minimize LLM token consumption.","exampleAgentPrompt":"Distill https://stripe.com/docs/payments/accept-a-payment into clean Markdown using budget mode, focused on 'payment intents setup', and keep it under 800 tokens so I can pass it to my model cheaply.","exampleUseCases":[{"title":"Research doc compression before LLM call","prompt":"Fetch https://arxiv.org/abs/2310.06825 and distill it into structured mode so I get the key metadata, tables, and abstract in as few tokens as possible before I send it to GPT."},{"title":"BM25-focused excerpt for a specific topic","prompt":"Pull https://docs.aws.amazon.com/lambda/latest/dg/welcome.html and give me only the sections relevant to 'cold start latency' using budget mode with a 500-token ceiling."},{"title":"Raw HTML cleanup for agent ingestion","prompt":"I have a blob of raw HTML from a scraped product page — distill it into clean Markdown so my agent can read it without blowing through its context window."}],"resultDescription":"Returns a JSON object containing: (1) distilled content under `data` — Markdown, structured JSON tables/metadata, skeleton outline, or BM25-ranked excerpt depending on mode; (2) `roi_proof` metrics including raw vs. distilled token counts, tokens saved, compression ratio percentage, ROI multiplier, and estimated LLM cost saved in USD; (3) optional `cache` status (HIT/MISS) with latency; (4) optional `billing` details including fee charged and payment method.","failureModes":["URL is unreachable or returns non-200 — fetch failure with error status","HTML content is empty or unparse-able — distillation returns minimal/empty data","mode=budget without query or max_tokens — may default to unfiltered output","Token budget too low (max_tokens < 20) — rejected by schema validation","Rate limiting or payment failure via x402 — 402 response requiring payment","Target site blocks headless fetching — content unavailable error"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to ingest web content but must stay within a token budget or minimize LLM API costs. It is especially valuable when the target URL is long-form (documentation, articles, reports) and only a relevant subsection is needed — use mode=budget with a BM25 query and max_tokens cap. Prefer it over raw web scraping when you need clean, agent-ready output (Markdown or structured JSON) rather than raw HTML. The built-in ROI proof metrics make it easy to audit compression gains per call.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:37:26.032Z","isFirstParty":false,"canonicalSlug":"mcp-compiler-agentdiet-dev-agentdiet-token-optimizer-url-html-939d5800"}