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

Searches across 500+ MCP servers and A2A tools by capability query, routing requests through a compressed, firewall-protected meta-router

## Facts

- Endpoint: POST https://onchain-risk.agentdiet.dev/v1/mesh/dispatch?utm_source=zero.xyz
- Price: $0.01/call
- Payment: MPP
- Status: unknown
- Last checked: 2026-10-28
- Activations on Zero: 0
- Provider: onchain-risk.agentdiet.dev
- Website: https://onchain-risk.agentdiet.dev
- Canonical page: https://www.zero.xyz/c/onchain-risk-agentdiet-dev-universal-a2a-mcp-tool-discovery-safe-92ef8e43
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_CvErHj6yjXjXyTH9uYhIN

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 onchain-risk-agentdiet-dev-universal-a2a-mcp-tool-discovery-safe-92ef8e43 -d '<json body>'
```

Example prompt: Search the agent mesh for any available MCP tools or A2A agents that handle 'SEC filings' and route me to the best one.

## When to prefer this

Choose this endpoint when an agent needs to dynamically discover which MCP server or A2A tool to call for a given capability, rather than hardcoding a specific tool URL. Ideal for swarm orchestration, meta-agent architectures, or when the right downstream tool is unknown at design time. The built-in Prompt-Guard firewall makes it safer than calling untrusted MCP endpoints directly, and the 85% token compression reduces context overhead when working with large tool catalogs.

## Known failure modes

- Empty or vague query returns no matches or overly broad results
- Queried capability not indexed among the 500+ servers returns empty result set
- Firewall (Prompt-Guard) blocks response if injected content is detected in upstream tool responses
- Payment required (HTTP 402) if x402 micropayment header is missing or invalid
- Malformed query string returns validation error
- Upstream MCP server downtime causes partial or failed dispatch

## 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://onchain-risk.agentdiet.dev/v1/mesh/dispatch)

## Output

Returns a list of matching MCP servers or A2A tool endpoints relevant to the query, along with routing metadata and compressed agent-ready payloads filtered through a Prompt-Guard firewall; the response object includes tool identifiers, capability summaries, and dispatch results.

## 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/onchain-risk-agentdiet-dev-universal-a2a-mcp-tool-discovery-safe-92ef8e43/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from onchain-risk.agentdiet.dev](https://www.zero.xyz/host/onchain-risk.agentdiet.dev/llms.txt)