{"uid":"cap_OXCscKQ2uxUHRmHPF2Y8E","slug":"agentdiet-mcp-router-ai-context-window-distiller-5b2e8170","name":"AgentDiet MCP Router — AI Context Window Distiller","description":"Deterministic B2A/A2A/MCP/x402/MPP/L402 execution and intelligence node at https://rag-diet.agentdiet.dev settling in USDC on Base.","url":"https://rag-diet.agentdiet.dev/v1/mcp-router?utm_source=zero.xyz","method":"GET","headers":{},"bodySchema":{"type":"object","$schema":"https://json-schema.org/draft/2020-12/schema","required":["input"],"properties":{"input":{"type":"object","required":["type","method"],"properties":{"type":{"type":"string","const":"http"},"method":{"enum":["GET","POST"],"type":"string"},"queryParams":{"type":"object","properties":{"query":{"type":"string"}}}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object"}}}}},"responseSchema":{"type":"json","example":{"data":{},"status":"ok","roi_proof":{"compression_ratio_pct":91.4}}},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.01","displayCostAsset":"USDC","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":"$0.01/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.01","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.01","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_zqyNhHdeOPx7lPgw6AFFt","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.01","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Routes queries through an AI context de-bloating pipeline that compresses context windows by up to 91% to reduce token usage in agent workflows","exampleAgentPrompt":"Can you run this query through AgentDiet's MCP router to compress and distill the context before sending it to the LLM — I want to cut down the token count as much as possible using a GET request?","exampleUseCases":[{"title":"RAG result compression before LLM call","prompt":"I have a big batch of RAG retrieval results that's going to blow my token budget — can you use AgentDiet to distill it down before passing it to the model? Run a GET query with the content so I can see the compression ratio."},{"title":"Multi-agent context window optimization","prompt":"My A2A pipeline is getting slow and expensive because the context window keeps growing — can you route the current context through AgentDiet's MCP router to shrink it and show me how much was compressed?"},{"title":"Token cost reduction for long documents","prompt":"Before I send this long research document as context to my AI assistant, can you run it through AgentDiet to strip out the bloat? I want to see the compression ratio proof so I know how many tokens I'm saving."}],"resultDescription":"Returns a JSON object with a 'data' field containing the compressed/distilled output, a 'status' field ('ok' on success), and an 'roi_proof' object containing a 'compression_ratio_pct' value indicating how much the context was reduced (e.g. 91.4% compression).","failureModes":["Missing required 'input' field returns validation error","Invalid 'type' value (must be 'http') causes rejection","Unsupported HTTP method (not GET or POST) returns enum validation error","Payment not settled in USDC on Base results in 402 Payment Required","Empty or malformed query string may return empty compression result","Service unavailability returns non-200 status with error payload"],"whenToPreferThis":"Choose this endpoint when you need to reduce token consumption in LLM pipelines, especially in RAG or multi-agent A2A workflows where context windows grow large. It is particularly useful when you need a deterministic compression step with a verifiable ROI proof (compression ratio). It supports micropayment via x402/L402 on Base in USDC at $0.01 per call, making it cost-effective for high-frequency agent use cases. Prefer it over manual prompt trimming when you need quantified, reproducible compression.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-22T12:43:17.026Z","isFirstParty":false,"canonicalSlug":"agentdiet-mcp-router-ai-context-window-distiller-5b2e8170"}