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

Searches an index of 500+ MCP servers and A2A tools by capability query, returning compressed results through a prompt-guarded meta-router.

## Facts

- Endpoint: GET https://github-audit.agentdiet.dev/v1/bundle-execute?utm_source=zero.xyz
- Price: $0.01/call
- Payment: MPP
- Status: unknown
- Last checked: 2026-10-21
- Activations on Zero: 0
- Provider: github-audit.agentdiet.dev
- Website: https://github-audit.agentdiet.dev
- Canonical page: https://www.zero.xyz/c/github-audit-agentdiet-dev-universal-a2a-mcp-tool-discovery-safe-d12cd3a9
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_5zdTDq94uH6JvY6WnuLKR

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 github-audit-agentdiet-dev-universal-a2a-mcp-tool-discovery-safe-d12cd3a9
```

Example prompt: Search the MCP and A2A tool index for capabilities related to 'github security' so I can find the right server to audit a repository.

## 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 hard-coding a specific tool. Especially useful when building swarm architectures, when the required capability may be served by multiple providers, or when token budget is constrained and compressed manifests are needed. Prefer this over direct MCP server lookup when safety filtering (Prompt-Guard) is required.

## Known failure modes

- Empty result set if query term is too niche or no indexed tools match
- Prompt-Guard firewall may block or filter queries containing potentially malicious or injection-like content
- Rate limiting or payment failure (HTTP 402) if x402 payment is not properly attached
- Timeout if the meta-router cannot reach enough upstream MCP servers within SLA
- Malformed query returns validation error

## 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://github-audit.agentdiet.dev/v1/bundle-execute)

## Output

Returns a compressed list of matching MCP servers or A2A tools relevant to the capability query, including endpoint details and tool manifests, filtered through a Prompt-Guard firewall for safety. Results feature up to 85% token compression to reduce context overhead.

## 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/github-audit-agentdiet-dev-universal-a2a-mcp-tool-discovery-safe-d12cd3a9/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from github-audit.agentdiet.dev](https://www.zero.xyz/host/github-audit.agentdiet.dev/llms.txt)
