# 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 2026-10-23).

Meta-router that searches across 500+ MCP servers and A2A tools, returning matching capabilities with prompt-guard firewall protection and 85% token compression

## Facts

- Endpoint: POST https://github-audit.agentdiet.dev/v1/execute?utm_source=zero.xyz
- Price: $0.01/call
- Payment: MPP
- Status: unknown
- Last checked: 2026-10-23
- 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-a9b4bebe
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_0iYaehD74nAwT5G-C-JUL

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-a9b4bebe -d '<json body>'
```

Example prompt: Search the MCP and A2A tool index for any available tools that handle GitHub security audits — I want to find the right endpoint to route my agent to.

## When to prefer this

Choose this endpoint when an agent needs to dynamically discover which MCP server or A2A tool to use for a given task, rather than hardcoding a specific tool. Especially useful for swarm architectures where agents must self-route to the right capability at runtime. Prefer this over direct endpoint calls when the right tool is unknown or when token budget is constrained (85% compression benefit).

## Known failure modes

- Empty or vague query returns no matches or low-confidence results
- Query matches no indexed tools, returning an empty result set
- Prompt-Guard firewall blocks queries containing injection patterns, returning a security rejection
- Upstream MCP server unavailable, causing partial or failed routing
- Malformed query string triggers input 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/execute)

## Output

Returns a list of matching MCP servers or A2A tools relevant to the search query, including endpoint metadata, capability descriptions, and routing information — delivered with 85% token compression and filtered through a Prompt-Guard firewall to block malicious payloads.

## 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-a9b4bebe/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)