ACP-MCP-Server

Instructions

Implementation Reference

• acp_mcp_server/run_orchestrator.py:314-342 (handler)

  The @mcp.tool()-decorated handler function that implements the core logic of get_async_run_result. It queries the run status, processes the output messages, and returns a formatted JSON result.

  @mcp.tool()
  async def get_async_run_result(run_id: str) -> str:
      """Get the result of an asynchronous run"""
      
      try:
          run = await orchestrator.get_run_status(run_id)
          
          result = {
              "run_id": run.run_id,
              "agent_name": run.agent_name,
              "status": run.status,
              "has_output": len(run.output) > 0,
              "error": run.error
          }
          
          if run.status == RunStatus.COMPLETED and run.output:
              # Convert output to readable format
              output_text = ""
              for message in run.output:
                  if isinstance(message, dict) and "parts" in message:
                      for part in message["parts"]:
                          if isinstance(part, dict) and "content" in part:
                              output_text += part["content"] + "\n"
              result["output"] = output_text.strip() if output_text else "No text content"
          
          return json.dumps(result, indent=2)
          
      except Exception as e:
          return f"Error: {e}"

• acp_mcp_server/server.py:87-87 (registration)

  Invocation of register_orchestrator_tools which defines and registers the get_async_run_result tool (along with related tools) with the FastMCP server instance.

  register_orchestrator_tools(self.mcp, self.orchestrator)