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

Indexes 500+ MCP servers and A2A tools, routes capability queries to the best match, and proxies responses through a prompt-injection firewall with token compression.

## Facts

- Endpoint: GET https://sec-intel.agentdiet.dev/v1/mesh/dispatch?utm_source=zero.xyz
- Price: $0.01/call
- Payment: MPP
- Status: unknown
- Last checked: 2026-10-21
- Activations on Zero: 0
- Provider: sec-intel.agentdiet.dev
- Website: https://sec-intel.agentdiet.dev
- Canonical page: https://www.zero.xyz/c/sec-intel-agentdiet-dev-universal-a2a-mcp-tool-discovery-safe-proxy-def67b02
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_a72u1mDm54s8SMlPx13aa

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 sec-intel-agentdiet-dev-universal-a2a-mcp-tool-discovery-safe-proxy-def67b02
```

Example prompt: Search the MCP mesh for a tool that handles 'SEC filings' and route me to the best match — I want the compressed, firewall-safe response.

## When to prefer this

Choose this endpoint when an AI agent needs to dynamically discover the right MCP server or A2A tool at runtime without hardcoding endpoints, especially when token budget is constrained (85% compression), when safety from prompt injection is required before proxying external agent calls, or when orchestrating a multi-agent swarm that needs a single routing layer across 500+ tools.

## Known failure modes

- No matching tool found for the query — returns empty or low-confidence result
- Query too vague to route to a specific MCP server
- Prompt-Guard firewall blocks a response flagged as prompt injection
- Endpoint URL provided fails verification — flagged as unsafe or unreachable
- Rate limiting or payment failure (x402) if quota exceeded

## 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://sec-intel.agentdiet.dev/v1/mesh/dispatch)

## Output

Returns a matched tool or MCP server from the 500+ indexed registry, including routing metadata, a token-compressed (up to 85%) response payload, and firewall clearance status from the Prompt-Guard layer. May include endpoint verification results if a URL was submitted.

## 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/sec-intel-agentdiet-dev-universal-a2a-mcp-tool-discovery-safe-proxy-def67b02/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from sec-intel.agentdiet.dev](https://www.zero.xyz/host/sec-intel.agentdiet.dev/llms.txt)