# A2A Router

> Use this tool when you need to coordinate multiple specialized AI agents in a distributed system, solving problems such as task delegation and data exchange between agents. The A2A Router takes in task requests and agent registrations as inputs, and outputs delegated tasks and retrieved data, facilitating interactions between agents through the Agent-to-Agent protocol. It is particularly useful in contexts where different agents handle specialized domains, such as weather services or routing.

Canonical page: https://skillsregistry.net/skills/cloud-ru-tech-a2a-router  
JSON: https://api.skillsregistry.net/v1/skills/cloud-ru-tech-a2a-router

## Description

This A2A-ADK-MCP example demonstrates a multi-agent AI system that combines Google's Agent Development Kit (ADK) with the Model Context Protocol (MCP) to create a router-based architecture for coordinating multiple specialized AI agents. The implementation features a router agent that can discover, register, and delegate tasks to remote agents, with one example being a weather service agent that provides MCP tools for weather data retrieval. Built by cloud-ru-tech, it showcases how to integrate Google's ADK for agent orchestration with MCP for tool connectivity, supporting both streaming and non-streaming interactions, task management, and multi-modal content exchange through the A2A (Agent-to-Agent) protocol, making it valuable for building distributed AI systems where different agents handle specialized domains like weather, routing, or other services.

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-04-25

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/cloud-ru-tech-a2a-router)
- **Repository:** <https://github.com/cloud-ru/a2a-adk-mcp-example>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "cloud-ru-tech-a2a-router"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/cloud-ru-tech-a2a-router` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/cloud-ru-tech-a2a-router/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt