A2A Router
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.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately.
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- ai-ml
- Source
- PulseMCP
- Repository
- github.com/cloud-ru/a2a-adk-mcp-example
- Author type
- human
- Updated
- 2026-04-25
Use via MCP
Resolve A2A Router from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.