{"uid":"cap_YJo-NA8PdZGthW0IufdNa","slug":"agentdiet-mcp-injection-firewall-38295c30","name":"AgentDiet MCP Injection Firewall","description":"Deterministic B2A/A2A/MCP/x402/MPP/L402 execution and intelligence node at https://status.agentdiet.dev settling in USDC on Base.","url":"https://status.agentdiet.dev/v1/mcp-injection-firewall?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":{"text":{"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":"0.005","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":"$0.005/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.005","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.005","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_vYSg0D9_I9KO3kZDO2apk","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.005","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Filters and validates MCP (Model Context Protocol) injections to protect AI agent context windows from bloat and malicious content.","exampleAgentPrompt":"Run this incoming MCP text payload through the AgentDiet injection firewall to check if it's safe and to see how much it compresses before I inject it into my agent's context window.","exampleUseCases":[{"title":"Blocking prompt injection in A2A pipeline","prompt":"I'm building an A2A pipeline where my agent receives instructions from external sources — can you run each incoming MCP payload through the injection firewall so I know it's safe before my agent acts on it?"},{"title":"Context window compression before LLM call","prompt":"Before I pass this retrieved document to the LLM, run it through the AgentDiet firewall so I get the compression ratio and can confirm it won't blow out my context window budget."},{"title":"Validating third-party MCP tool outputs","prompt":"My agent is calling third-party MCP tools and I'm worried about malicious content sneaking in — can you filter each tool response through the MCP injection firewall and only pass it through if the status is ok?"}],"resultDescription":"Returns a JSON object with a status field ('ok' or error), a data payload containing the processed/filtered content, and an roi_proof object showing the compression_ratio_pct achieved (e.g. 91.4%), confirming the safety and compactness of the injected context.","failureModes":["Missing or malformed 'input' object returns validation error","Invalid method enum value (not GET or POST) causes schema rejection","Empty or absent 'text' query parameter may return empty data with no compression proof","Service unavailability returns non-200 status with no ROI proof","Payment not settled in USDC on Base results in 402 Payment Required response"],"whenToPreferThis":"Choose this endpoint when you need to both validate and compress incoming MCP payloads before injecting them into an agent context window, especially in A2A or B2A pipelines where untrusted external content is involved. It is particularly suited for agents operating under token budget constraints who need proof of compression alongside safety validation, and for workflows using x402/L402 micropayment-gated APIs on Base.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-22T12:44:02.229Z","isFirstParty":false,"canonicalSlug":"agentdiet-mcp-injection-firewall-38295c30"}