PicoScope MCP Server

Instructions

Implementation Reference

• src/picoscope_mcp/tools/acquisition.py:127-150 (handler)

  The MCP tool handler for 'start_streaming'. Decorated with @mcp.tool(), defines input schema via type hints, and contains the core logic (currently stubbed with TODO).

  @mcp.tool()
  def start_streaming(
      sample_interval_ns: int,
      buffer_size: int = 100000,
      auto_stop: bool = False,
      max_samples: int = 0,
  ) -> dict[str, Any]:
      """Start streaming data acquisition.
  
      Args:
          sample_interval_ns: Sample interval in nanoseconds.
          buffer_size: Size of streaming buffer.
          auto_stop: Whether to automatically stop after max_samples.
          max_samples: Maximum samples to capture (0 = continuous).
  
      Returns:
          Dictionary containing streaming status and configuration.
      """
      # TODO: Implement streaming mode
      return {
          "status": "not_implemented",
          "sample_interval_ns": sample_interval_ns,
          "buffer_size": buffer_size,
      }

• src/picoscope_mcp/server.py:17-17 (registration)

  Top-level registration call in the main server file that invokes register_acquisition_tools(mcp), thereby registering the 'start_streaming' tool among others.

  register_acquisition_tools(mcp)

• src/picoscope_mcp/device_manager.py:485-503 (helper)

  Supporting method in the device manager class intended for the actual streaming implementation, called potentially from the tool handler.

  def start_streaming(
      self, sample_interval_ns: int, buffer_size: int
  ) -> bool:
      """Start streaming mode.
  
      Args:
          sample_interval_ns: Sample interval in nanoseconds.
          buffer_size: Buffer size for streaming.
  
      Returns:
          True if successful, False otherwise.
      """
      if not self.is_connected():
          return False
  
      # TODO: Implement streaming mode
      # This will need to set up buffers and call ps*RunStreaming
  
      return True