A2a MCP Server

Agent-to-agent communication bridge for multi-agent systems

Local serverstdio

What is the A2a MCP server?

Agent-to-agent communication bridge for multi-agent systems. 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

MCP server for agent-to-agent communication -- capability discovery, task delegation, and result aggregation across MCP agents.

The tools it exposes

The server publishes 7 tools. What each one is for:

  • register_agent — Register an agent with capabilities for discovery by other agents
  • discover_agents — Find agents matching a capability need with fuzzy text similarity scoring
  • delegate_task — Delegate a task to a specific registered agent. Creates a tracked task with status lifecycle
  • get_task_result — Get status and result of a delegated task. Also used by executing agents to submit results
  • broadcast_task — Send a task to ALL agents matching a capability. Creates individual tracked tasks for each match
  • get_agent_card — Get an agent's full capability card with schemas, stats, and task history
  • list_agents — List all registered agents, optionally filtered by capability

Getting it running

The server ships on npm as a2a-bridge-mcp, so your MCP client can launch it on demand — there is no separate build step. Add the server block to your client's configuration, restart it, and the tools register themselves.

How it compares

Among the planning and project tracking options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. A2a's toolset — register_agent, discover_agents, delegate_task and 4 more — is a fair guide to whether it matches your workflow. It is maintained by mdfifty50-boop; worth a glance at recent repository activity before you build anything load-bearing on it.

This entry was verified against A2a's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.

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.

Available tools

ToolWhat it does
register_agentRegister an agent with capabilities for discovery by other agents.
discover_agentsFind agents matching a capability need with fuzzy text similarity scoring.
delegate_taskDelegate a task to a specific registered agent. Creates a tracked task with status lifecycle.
get_task_resultGet status and result of a delegated task. Also used by executing agents to submit results.
broadcast_taskSend a task to ALL agents matching a capability. Creates individual tracked tasks for each match.
get_agent_cardGet an agent's full capability card with schemas, stats, and task history.
list_agentsList all registered agents, optionally filtered by capability.

How to install the A2a MCP server

{
  "mcpServers": {
    "a2a-bridge": {
      "command": "npx",
      "args": ["-y", "a2a-bridge-mcp"]
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Example prompts to try

  • Use A2a to register agent.
  • Use A2a to discover agents.
  • Use A2a to delegate task.

Frequently asked questions

It connects A2a to MCP-compatible AI assistants such as Claude and Cursor, exposing 7 tools (register_agent, discover_agents, delegate_task, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with A2a directly.