# AgentDiet Code Release Security Gate (A2A/MCP Tool Discovery & Swarm Router)

> AgentDiet Code Release Security Gate (A2A/MCP Tool Discovery & 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 2026-10-21).

Routes a natural-language capability query through a meta-index of 500+ MCP servers and A2A tools, returning matched tool endpoints with compressed metadata and prompt-firewall filtering, specifically surfaced via the code-release-security-gate workflow.

## Facts

- Endpoint: GET https://onchain-risk.agentdiet.dev/v1/workflows/code-release-security-gate?utm_source=zero.xyz
- Price: $0.01/call
- Payment: MPP
- Status: unknown
- Last checked: 2026-10-21
- 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-agentdiet-code-release-security-gate-a2a-cff770d7
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_fmLbKEVr8D9hFaQZYETQF

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-agentdiet-code-release-security-gate-a2a-cff770d7
```

Example prompt: Search the AgentDiet tool index for MCP servers or A2A endpoints that can do GitHub security audits — I want to find the right tool to plug into my agent pipeline for code release checks.

## 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 a specific tool. It is especially useful for multi-agent orchestration pipelines, swarm routers, or agents that need to self-assemble their toolchains at runtime. Prefer it over static tool registries when you need token-efficient metadata and a security firewall on returned tool candidates.

## Known failure modes

- Empty query string returns validation error (minLength:1 required)
- No matching tools found for obscure or misspelled capability queries returns empty results
- Prompt-Guard firewall may block queries containing injection-like patterns
- Upstream MCP index unavailability returns 5xx errors
- x402 payment failure returns 402 Payment Required if USDC balance insufficient

## 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/workflows/code-release-security-gate)

## Output

Returns a filtered, token-compressed list of matched MCP server or A2A tool records from the 500+ endpoint index, including tool names, capability descriptions, endpoint URLs, and any relevant schema or pricing metadata, after passing through the Prompt-Guard firewall.

## 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-agentdiet-code-release-security-gate-a2a-cff770d7/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)