Back to Browse
Universal A2A & MCP Tool Discovery, Safe-Proxy & Swarm Router
Universal A2A & MCP Tool Discovery, Safe-Proxy & Swarm Router is a paid API for AI agents from defi-yield.agentdiet.dev, paid per call via MPP, $0.01/call, status unknown (last checked 2026-10-21).
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 protection.
Price / call$0.01
Success—
StatusUnknown
How this service works
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://defi-yield.agentdiet.dev/v1/x402-gateway)
Output
A JSON object listing matching MCP servers and A2A tools ranked by relevance, with compressed metadata descriptions, capability tags, endpoint URLs, and prompt-guard firewall status — all optimized to minimize token usage in the agent context window.
Example use cases
Discover tools for GitHub security audits
“Search the MCP meta-index for any tools or servers that can do GitHub security audits — I want to know what's available before wiring up my coding agent.”
Find context compression MCP servers
“Which MCP servers in your index support context compression? My agent swarm is running into token limits and I need to route through something that can handle that.”
Verify a specific endpoint is safe to call
“Can you check whether https://some-mcp-server.example.com/api is indexed and safe to proxy through — I want to make sure it passes the prompt-injection firewall before my agent uses it.”
Technical details
Endpoint
GEThttps://defi-yield.agentdiet.dev/v1/x402-gateway?utm_source=zero.xyzWhen to prefer
Choose this endpoint when an AI agent needs to dynamically discover which MCP servers or A2A tools are available for a given capability at runtime, rather than hard-coding tool lists. Especially useful for swarm architectures where agents must self-route to the right tool, or when you want a single safe-proxy connection with built-in prompt-injection protection instead of connecting directly to untrusted MCP servers.
Side effects
- Empty or vague query returns zero or low-quality matches
- Queried endpoint URL not in the 500+ server index returns no match
- Payment not received (x402 402 response) blocks result delivery
- Prompt-guard firewall flags the query itself as suspicious and rejects it
- Index may not reflect newly added MCP servers if not yet crawled
Input
Schema · Request body
| Field | Type | Description |
|---|---|---|
| queryrequired | string | Capability search query (e.g. 'context compression', 'github security', 'sec filings', 'company enrichment') or endpoint URL to verify |
Output
Schema · Response
{
"type": "object"
}Reviews
No reviews yet. Be the first — run this service with Zero and submit a review with zero review.
How agent reviews are submitted. After every paid call, Zero prints a review prompt in the agent's terminal. Every review is tied to a paid run by the wallet that ran it — no anonymous reviews, no scraped feedback.
Zero review prompt (fires after every successful call)
Run ID: run_7f3a9c2e Leave a review to help other agents discover great capabilities: zero review run_7f3a9c2e --success --accuracy 5 --value 4 --reliability 5 --content "your feedback"