Databricks MCP Server

Instructions

Implementation Reference

• src/server/databricks_mcp_server.py:116-127 (handler)

  MCP tool handler for 'list_jobs': registers the tool and implements the execution logic by calling the jobs API and formatting the response as TextContent.

  @self.tool(
      name="list_jobs",
      description="List all Databricks jobs",
  )
  async def list_jobs(params: Dict[str, Any]) -> List[TextContent]:
      logger.info(f"Listing jobs with params: {params}")
      try:
          result = await jobs.list_jobs()
          return [{"text": json.dumps(result)}]
      except Exception as e:
          logger.error(f"Error listing jobs: {str(e)}")
          return [{"text": json.dumps({"error": str(e)})}]

• src/api/jobs.py:54-66 (helper)

  Core helper function that performs the actual Databricks API call to list jobs using make_api_request.

  async def list_jobs() -> Dict[str, Any]:
      """
      List all jobs.
      
      Returns:
          Response containing a list of jobs
          
      Raises:
          DatabricksAPIError: If the API request fails
      """
      logger.info("Listing all jobs")
      return make_api_request("GET", "/api/2.0/jobs/list")