A2A MCP Server

A mcp server that bridges the Model Context Protocol (MCP) with the Agent-to-Agent (A2A) protocol, enabling MCP-compatible AI assistants (like

Local serverstdioPython

What is the A2A MCP server?

A mcp server that bridges the Model Context Protocol (MCP) with the Agent-to-Agent (A2A) protocol, enabling MCP-compatible AI assistants (like Claude) to seamlessly interact with A2A agents. That is what the a2a mcp server brings to an AI assistant: the same capability, reachable through the Model Context Protocol rather than a separate app or dashboard.

The short version

This project serves as an integration layer between two cutting-edge AI agent protocols:

  • Agent Management —
  • Register A2A agents with the bridge server
  • List all registered agents
  • Unregister agents when no longer needed
  • Communication —
  • Send messages to A2A agents and receive responses

Getting it running

@smithery/cli on npm is all you need. Most clients run it directly, so configuration is a few lines and a restart.

The tools it exposes

The server publishes 2 tools. What each one is for:

  • Demo — The Demo tool exposed by this server
  • Claude — Claude can use A2A agents through the MCP tools provided by this server. Here's how to set it up:

What it needs from you

Configuration is passed through the environment: MCP_TRANSPORT, PYTHONPATH, MCP_HOST, MCP_PORT, MCP_PATH, MCP_SSE_PATH, MCP_DEBUG. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.

Things to watch

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

How it compares

This sits in the planning and project tracking group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. A2A's toolset — Demo, Claude — is a fair guide to whether it matches your workflow. It is maintained by GongRzhe; worth a glance at recent repository activity before you build anything load-bearing on it.

We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.

Available tools

ToolWhat it does
DemoThe Demo tool exposed by this server.
ClaudeClaude can use A2A agents through the MCP tools provided by this server. Here's how to set it up:

How to install the A2A MCP server

{
  "mcpServers": {
    "a2a": {
      "command": "npx",
      "args": ["-y", "@smithery/cli"],
      "env": {
        "MCP_TRANSPORT": "your-value",
        "PYTHONPATH": "your-value",
        "MCP_HOST": "your-value",
        "MCP_PORT": "your-value",
        "MCP_PATH": "your-value",
        "MCP_SSE_PATH": "your-value",
        "MCP_DEBUG": "your-value"
      }
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Configuration

VariableDescriptionRequired
MCP_TRANSPORTConfiguration value read at startup.Optional
PYTHONPATHFilesystem location the server is allowed to use.Optional
MCP_HOSTEndpoint or connection string the server talks to.Optional
MCP_PORTConfiguration value read at startup.Optional
MCP_PATHFilesystem location the server is allowed to use.Optional
MCP_SSE_PATHFilesystem location the server is allowed to use.Optional
MCP_DEBUGConfiguration value read at startup.Optional

Example prompts to try

  • Use A2A to Demo.
  • Use A2A to Claude.

Frequently asked questions

It connects A2A to MCP-compatible AI assistants such as Claude and Cursor, exposing 2 tools (Demo, Claude) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with A2A directly.