{"uid":"cap_NSJB36kpxitzIlkCGdLSP","slug":"prompt-guard-agentdiet-dev-universal-a2a-mcp-tool-discovery-safe-413de47d","name":"Universal A2A & MCP Tool Discovery, Safe-Proxy & Swarm Router","description":"Single-connection meta-router indexing 500+ MCP servers & A2A tools with 85% token compression and Prompt-Guard firewall. (Live x402 v2, IETF MPP & MCP endpoint at https://prompt-guard.agentdiet.dev/v1/web-rag-shield-dag)","url":"https://prompt-guard.agentdiet.dev/v1/web-rag-shield-dag?utm_source=zero.xyz","method":"POST","headers":{},"bodySchema":{"type":"object","required":["query"],"properties":{"query":{"type":"string","minLength":1,"description":"Capability search query (e.g. 'context compression', 'github security', 'sec filings', 'company enrichment') or endpoint URL to verify"}}},"responseSchema":{"type":"object"},"example":null,"exampleRequest":null,"tags":[],"displayCostAmount":"0.01","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":"$0.01/call","primary":{"kind":"static","protocol":"mpp","network":"tempo","amountUsd":"0.01","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"mpp","network":"tempo","amountUsd":"0.01","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_j8bgUcHYGRJgImpOOP_uB","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.01","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"prompt-guard.agentdiet.dev","brandSlug":"prompt-guard-agentdiet-dev-mpp","brandBaseUrl":"https://prompt-guard.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Searches a meta-index of 500+ MCP servers and A2A tools by capability query, returning matching endpoints with 85% token-compressed results and prompt-injection firewall protection.","exampleAgentPrompt":"Search the MCP and A2A tool index for any servers that handle 'context compression' and tell me which ones are available — I want to find the best option to wire into my agent pipeline.","exampleUseCases":[{"title":"Agent pipeline tool discovery","prompt":"I need to find MCP servers that can handle SEC filings and financial intelligence — search the tool index for anything relevant so I can plug the right one into my agent."},{"title":"Security-aware capability routing","prompt":"Can you search the A2A and MCP tool registry for anything related to 'github security' or 'code auditing' so I know which tools are available for my automated review pipeline?"},{"title":"Agent swarm capability lookup","prompt":"My swarm agent needs to do B2B lead enrichment — search the meta-router index for MCP or A2A tools that cover company enrichment or contact data so I can route tasks to the right server."}],"resultDescription":"A token-compressed listing of matching MCP servers and A2A tool endpoints relevant to the capability query, including tool names, descriptions, and endpoint URLs, filtered through the Prompt-Guard firewall to block prompt-injection payloads.","failureModes":["Empty or overly generic query returns low-relevance or no matching tools","Malicious or prompt-injection-containing queries are blocked by the Prompt-Guard firewall and return an error","Unknown or unsupported capability domains may return empty result sets","Network or upstream MCP index unavailability returns a 5xx error","Payment not completed (HTTP 402) if x402 micropayment handshake fails"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to dynamically discover which MCP servers or A2A tools exist for a given capability at runtime, rather than hardcoding tool references. It is especially useful for swarm architectures, meta-agent orchestrators, or pipelines that need to adapt to new tools without redeployment. Prefer it over manual tool registries when you want built-in prompt-injection protection and compressed token output for LLM-friendly consumption.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:35:10.815Z","isFirstParty":false,"canonicalSlug":"prompt-guard-agentdiet-dev-universal-a2a-mcp-tool-discovery-safe-bcdfb4b9"}