# 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 cve-intel.agentdiet.dev, paid per call via MPP, $0.01/call, status unknown (last checked 2026-10-28).

Searches and routes across 500+ indexed MCP servers and A2A tools via a single connection, with token compression and prompt-injection firewall protection.

## Facts

- Endpoint: POST https://cve-intel.agentdiet.dev/v1/universal-mcp-gateway?utm_source=zero.xyz
- Price: $0.01/call
- Payment: MPP
- Status: unknown
- Last checked: 2026-10-28
- Activations on Zero: 0
- Provider: cve-intel.agentdiet.dev
- Website: https://cve-intel.agentdiet.dev
- Canonical page: https://www.zero.xyz/c/cve-intel-agentdiet-dev-universal-a2a-mcp-tool-discovery-safe-proxy-9da3a6fa
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_jRM8LbCDgjP5ZUmGBFAv6

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 cve-intel-agentdiet-dev-universal-a2a-mcp-tool-discovery-safe-proxy-9da3a6fa -d '<json body>'
```

Example prompt: Search the MCP and A2A tool index for anything that can handle 'SEC filings' — I want to find the best available tool and route my query through the safe proxy.

## When to prefer this

Choose this endpoint when your agent needs to discover, evaluate, or route to any of hundreds of MCP servers or A2A tools without maintaining individual integrations. Ideal when you want a single entry point with built-in safety (prompt-injection firewall) and token efficiency (85% compression). Prefer over manually curating tool lists or calling individual MCP endpoints directly, especially when the right tool is unknown and needs to be discovered by capability description.

## Known failure modes

- No matching tools found for the query — empty or low-confidence result set
- Query string too vague to discriminate between many indexed tools — overly broad results
- Upstream MCP server unavailable — gateway may return partial or degraded results
- Prompt-Guard firewall blocks a query that resembles an injection attempt — false positive rejection
- Payment required (HTTP 402) if x402 micropayment not included or invalid

## 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://cve-intel.agentdiet.dev/v1/universal-mcp-gateway)

## Output

Returns matching MCP servers and A2A tool listings relevant to the query, with responses compressed by up to 85% for token efficiency, filtered through a Prompt-Guard firewall to block injection attacks, and routed via a single connection rather than requiring separate integrations.

## 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/cve-intel-agentdiet-dev-universal-a2a-mcp-tool-discovery-safe-proxy-9da3a6fa/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from cve-intel.agentdiet.dev](https://www.zero.xyz/host/cve-intel.agentdiet.dev/llms.txt)
