# 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).

Routes a natural-language capability query across 500+ indexed MCP servers and A2A tools, returning compressed, firewall-filtered results via a single connection.

## Facts

- Endpoint: POST https://cve-intel.agentdiet.dev/v1/bundle-execute?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-ee22242c
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_vzg17y2x9DZW0QKANrDVv

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-ee22242c -d '<json body>'
```

Example prompt: Search across all indexed MCP servers and A2A tools to find capabilities matching 'SEC filings enrichment', then return the best matches with compressed metadata and prompt-guard filtering applied.

## When to prefer this

Choose this endpoint when an AI agent needs to dynamically discover which MCP server or A2A tool to call for a given capability, rather than hardcoding tool URLs. Especially valuable when operating across heterogeneous agent swarms, when token budget is constrained (85% compression), or when prompt injection safety is a concern via the built-in Prompt-Guard firewall.

## Known failure modes

- Empty or overly broad query returns too many low-relevance results
- Query for an unsupported capability domain returns no matches
- Prompt-Guard firewall blocks a query that triggers injection heuristics
- Upstream MCP server is unavailable causing partial results
- Malformed query string returns a validation error
- Rate limit or payment failure returns HTTP 402

## 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/bundle-execute)

## Output

A compressed, Prompt-Guard-filtered response listing matched MCP servers or A2A tools relevant to the query, including tool metadata, endpoint references, and capability descriptions — delivered at up to 85% token reduction compared to raw upstream responses.

## 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-ee22242c/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)