{"uid":"cap_V74goW8IjGUm7RuaVNNnj","slug":"mcp-compiler-agentdiet-dev-web-url-distillation-rag-token-compressor-a5fe7ccf","name":"Web URL Distillation & RAG Token Compressor","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/rag-token-diet)","url":"https://mcp-compiler.agentdiet.dev/v1/rag-token-diet?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_QRiYRPsaDv6d_Ww1OOWid","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 raw HTML and distills it into compact, agent-ready tokens using BM25 budget control and multiple extraction modes","exampleAgentPrompt":"Distill this page into compact markdown so I can use it in my RAG pipeline without blowing my context window: https://stripe.com/docs/payments — use budget mode with a 500-token ceiling and focus the BM25 query on 'payment intent'.","exampleUseCases":[{"title":"RAG pipeline documentation ingestion","prompt":"Fetch and compress the Stripe docs page at builtin://stripe-docs into structured markdown under 800 tokens so I can include it in my agent's context without hitting token limits."},{"title":"Relevance-focused budget extraction","prompt":"Grab the page at https://openai.com/research/gpt-4 and pull out only the content relevant to 'safety benchmarks' — keep it under 300 tokens using budget mode."},{"title":"Skeleton outline for long article","prompt":"Give me a skeleton outline of https://en.wikipedia.org/wiki/Transformer_(machine_learning_model) so I can see the document structure without reading the whole thing."}],"resultDescription":"Returns a distilled payload with a 'data' object containing the compressed content (markdown, structured JSON tables/metadata, skeleton outline, or BM25-ranked excerpt), plus an 'roi_proof' object showing raw token count, distilled token count, tokens saved, compression ratio percentage, estimated LLM cost saved in USD, and ROI multiplier. Also includes cache status and billing details.","failureModes":["Invalid or unreachable URL returns an error status","mode=budget without a query or max_tokens may return unfiltered content","HTML too large may exceed processing limits","Paywalled or bot-blocked URLs may return incomplete content","max_tokens below 20 is rejected by schema validation","Payment required (HTTP 402) if no valid x402 payment method is provided"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to read a live webpage but must stay within a token budget — especially for RAG pipelines, documentation grounding, or any workflow where raw HTML would consume too many context tokens. The BM25 budget mode makes it uniquely suited for query-focused extraction where only topically relevant sections matter. Prefer this over generic scrapers when you need both compression metrics (ROI proof) and multiple output formats (markdown, structured, skeleton).","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:22:41.405Z","isFirstParty":false,"canonicalSlug":"mcp-compiler-agentdiet-dev-web-url-distillation-rag-token-compressor-a5fe7ccf"}