MCP Background Job Server

Instructions

Implementation Reference

• src/mcp_background_job/server.py:73-94 (handler)

  MCP tool handler for 'get_job_output', decorated with @mcp.tool(). Validates input with Pydantic Field, delegates to JobManager service, handles errors with ToolError.

  @mcp.tool()
  async def get_job_output(
      job_id: str = Field(..., description="Job ID to get output from"),
  ) -> ProcessOutput:
      """Get the complete stdout and stderr output of a job.
  
      Args:
          job_id: The UUID of the job to get output from
  
      Returns:
          ProcessOutput containing the complete stdout and stderr content
      """
      try:
          job_manager = get_job_manager()
          job_output = await job_manager.get_job_output(job_id)
          return job_output
      except KeyError:
          raise ToolError(f"Job {job_id} not found")
      except Exception as e:
          logger.error(f"Error getting job output for {job_id}: {e}")
          raise ToolError(f"Failed to get job output: {str(e)}")

• src/mcp_background_job/models.py:42-47 (schema)

  Pydantic BaseModel defining the output schema for the tool, with stdout and stderr fields.

  class ProcessOutput(BaseModel):
      """Structured stdout/stderr output from a process."""
  
      stdout: str = Field(..., description="Standard output content")
      stderr: str = Field(..., description="Standard error content")

• src/mcp_background_job/service.py:206-226 (helper)

  JobManager method implementing the core logic to fetch complete process output via ProcessWrapper for the specified job.

  async def get_job_output(self, job_id: str) -> ProcessOutput:
      """Get full stdout/stderr output.
  
      Args:
          job_id: Job identifier
  
      Returns:
          ProcessOutput with complete stdout and stderr
  
      Raises:
          KeyError: If job_id doesn't exist
      """
      if job_id not in self._jobs:
          raise KeyError(f"Job {job_id} not found")
  
      process_wrapper = self._processes.get(job_id)
      if process_wrapper is None:
          return ProcessOutput(stdout="", stderr="")
  
      return process_wrapper.get_output()