ServiceNow MCP Server

Instructions

Implementation Reference

• src/servicenow_mcp/tools/change_tools.py:758-857 (handler)

  Main execution function for the approve_change tool. It validates parameters, queries the approval record, updates it to approved state, and advances the change request to implement state.

  def approve_change(
      auth_manager: AuthManager,
      server_config: ServerConfig,
      params: Dict[str, Any],
  ) -> Dict[str, Any]:
      """
      Approve a change request in ServiceNow.
  
      Args:
          auth_manager: The authentication manager.
          server_config: The server configuration.
          params: The parameters for approving a change request.
  
      Returns:
          The result of the approval.
      """
      # Unwrap and validate parameters
      result = _unwrap_and_validate_params(
          params, 
          ApproveChangeParams,
          required_fields=["change_id"]
      )
      
      if not result["success"]:
          return result
      
      validated_params = result["params"]
      
      # Get the instance URL
      instance_url = _get_instance_url(auth_manager, server_config)
      if not instance_url:
          return {
              "success": False,
              "message": "Cannot find instance_url in either server_config or auth_manager",
          }
      
      # Get the headers
      headers = _get_headers(auth_manager, server_config)
      if not headers:
          return {
              "success": False,
              "message": "Cannot find get_headers method in either auth_manager or server_config",
          }
      
      # First, find the approval record
      approval_query_url = f"{instance_url}/api/now/table/sysapproval_approver"
      
      query_params = {
          "sysparm_query": f"document_id={validated_params.change_id}",
          "sysparm_limit": 1,
      }
      
      try:
          approval_response = requests.get(approval_query_url, headers=headers, params=query_params)
          approval_response.raise_for_status()
          
          approval_result = approval_response.json()
          
          if not approval_result.get("result") or len(approval_result["result"]) == 0:
              return {
                  "success": False,
                  "message": "No approval record found for this change request",
              }
          
          approval_id = approval_result["result"][0]["sys_id"]
          
          # Now, update the approval record to approved
          approval_update_url = f"{instance_url}/api/now/table/sysapproval_approver/{approval_id}"
          headers["Content-Type"] = "application/json"
          
          approval_data = {
              "state": "approved",
          }
          
          if validated_params.approval_comments:
              approval_data["comments"] = validated_params.approval_comments
          
          approval_update_response = requests.patch(approval_update_url, json=approval_data, headers=headers)
          approval_update_response.raise_for_status()
          
          # Finally, update the change request state to "implement"
          change_url = f"{instance_url}/api/now/table/change_request/{validated_params.change_id}"
          
          change_data = {
              "state": "implement",  # This may vary depending on ServiceNow configuration
          }
          
          change_response = requests.patch(change_url, json=change_data, headers=headers)
          change_response.raise_for_status()
          
          return {
              "success": True,
              "message": "Change request approved successfully",
          }
      except requests.exceptions.RequestException as e:
          logger.error(f"Error approving change: {e}")
          return {
              "success": False,
              "message": f"Error approving change: {str(e)}",
          }

• src/servicenow_mcp/tools/change_tools.py:91-97 (schema)

  Pydantic model defining the input schema for the approve_change tool, including required change_id and optional fields.

  class ApproveChangeParams(BaseModel):
      """Parameters for approving a change request."""
  
      change_id: str = Field(..., description="Change request ID or sys_id")
      approver_id: Optional[str] = Field(None, description="ID of the approver")
      approval_comments: Optional[str] = Field(None, description="Comments for the approval")

• src/servicenow_mcp/utils/tool_utils.py:521-527 (registration)

  Registration of the approve_change tool in the central tool_definitions dictionary, mapping name to handler, schema, return type, description, and serialization method.

  "approve_change": (
      approve_change_tool,
      ApproveChangeParams,
      str,
      "Approve a change request",
      "str",  # Tool returns simple message
  ),

• src/servicenow_mcp/utils/tool_utils.py:69-70 (registration)

  Import and alias of the approve_change handler function as approve_change_tool for use in tool registration.

      approve_change as approve_change_tool,
  )

• src/servicenow_mcp/tools/change_tools.py:107-159 (helper)

  Helper function used by approve_change to unwrap, validate parameters against the Pydantic schema, and check required fields.

  def _unwrap_and_validate_params(params: Any, model_class: Type[T], required_fields: List[str] = None) -> Dict[str, Any]:
      """
      Helper function to unwrap and validate parameters.
      
      Args:
          params: The parameters to unwrap and validate.
          model_class: The Pydantic model class to validate against.
          required_fields: List of required field names.
          
      Returns:
          A tuple of (success, result) where result is either the validated parameters or an error message.
      """
      # Handle case where params might be wrapped in another dictionary
      if isinstance(params, dict) and len(params) == 1 and "params" in params and isinstance(params["params"], dict):
          logger.warning("Detected params wrapped in a 'params' key. Unwrapping...")
          params = params["params"]
      
      # Handle case where params might be a Pydantic model object
      if not isinstance(params, dict):
          try:
              # Try to convert to dict if it's a Pydantic model
              logger.warning("Params is not a dictionary. Attempting to convert...")
              params = params.dict() if hasattr(params, "dict") else dict(params)
          except Exception as e:
              logger.error(f"Failed to convert params to dictionary: {e}")
              return {
                  "success": False,
                  "message": f"Invalid parameters format. Expected a dictionary, got {type(params).__name__}",
              }
      
      # Validate required parameters are present
      if required_fields:
          for field in required_fields:
              if field not in params:
                  return {
                      "success": False,
                      "message": f"Missing required parameter '{field}'",
                  }
      
      try:
          # Validate parameters against the model
          validated_params = model_class(**params)
          return {
              "success": True,
              "params": validated_params,
          }
      except Exception as e:
          logger.error(f"Error validating parameters: {e}")
          return {
              "success": False,
              "message": f"Error validating parameters: {str(e)}",
          }