# 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 prompt-guard.agentdiet.dev, paid per call via MPP, $0.01/call, status unknown (last checked 2026-10-21).

Searches and proxies 500+ MCP servers and A2A tools via a single connection, with token compression and prompt injection firewall

## Facts

- Endpoint: GET https://prompt-guard.agentdiet.dev/v1/execute?utm_source=zero.xyz
- Price: $0.01/call
- Payment: MPP
- Status: unknown
- Last checked: 2026-10-21
- Activations on Zero: 0
- Provider: prompt-guard.agentdiet.dev
- Website: https://prompt-guard.agentdiet.dev
- Canonical page: https://www.zero.xyz/c/prompt-guard-agentdiet-dev-universal-a2a-mcp-tool-discovery-safe-e1aeab54
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_7eEzIjTE-aRtktYeGZDAB

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability prompt-guard-agentdiet-dev-universal-a2a-mcp-tool-discovery-safe-e1aeab54
```

Example prompt: Search the MCP tool index for anything related to 'SEC filings' so I can find which servers and A2A endpoints support that capability — run the query through the prompt-guard firewall and give me the compressed results.

## When to prefer this

Choose this endpoint when an AI agent needs to discover which MCP servers or A2A tools support a given capability across a large registry without connecting to each individually. Ideal when token budget is tight (85% compression), when prompt injection safety is a concern, or when orchestrating multi-tool swarms from a single connection point. Prefer over direct MCP server connections when the specific tool server is unknown.

## Known failure modes

- No matching tools found for an obscure query — returns empty result set
- Query string too short or vague — may return low-relevance results
- Endpoint URL verification may time out if the remote server is unresponsive
- Prompt-Guard firewall may block or flag queries containing injection-like patterns
- Payment not completed (HTTP 402) — call not executed
- Rate limiting or quota exhaustion at $0.01/call

## 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://prompt-guard.agentdiet.dev/v1/execute)

## Output

A structured response listing matching MCP servers and A2A tool endpoints for the query, with compressed tool manifests (up to 85% token reduction) and any prompt-injection risk flags from the firewall. When given a URL, returns compliance and verification metadata for that endpoint.

## Request schema (JSON Schema)

```json
{
 "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"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "object"
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/prompt-guard-agentdiet-dev-universal-a2a-mcp-tool-discovery-safe-e1aeab54/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from prompt-guard.agentdiet.dev](https://www.zero.xyz/host/prompt-guard.agentdiet.dev/llms.txt)