Skip to main content
Glama
echelon-ai-labs

ServiceNow MCP Server

update_workflow

Modify workflow settings in ServiceNow by updating attributes like name, description, active status, and associated table using the Workflow ID.

Instructions

Update an existing workflow in ServiceNow

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
paramsYes

Implementation Reference

  • The main execution function (handler) for the update_workflow tool. It validates input using UpdateWorkflowParams, prepares the update payload, and performs a PATCH request to the ServiceNow wf_workflow table endpoint.
    def update_workflow(
        auth_manager: AuthManager,
        server_config: ServerConfig,
        params: Dict[str, Any],
    ) -> Dict[str, Any]:
        """
        Update an existing workflow in ServiceNow.
        
        Args:
            auth_manager: Authentication manager
            server_config: Server configuration
            params: Parameters for updating a workflow
            
        Returns:
            Dict[str, Any]: Updated workflow details
        """
        # Unwrap parameters if needed
        params = _unwrap_params(params, UpdateWorkflowParams)
        
        # Get the correct auth_manager and server_config
        try:
            auth_manager, server_config = _get_auth_and_config(auth_manager, server_config)
        except ValueError as e:
            logger.error(f"Error getting auth and config: {e}")
            return {"error": str(e)}
        
        workflow_id = params.get("workflow_id")
        if not workflow_id:
            return {"error": "Workflow ID is required"}
        
        # Prepare data for the API request
        data = {}
        
        if params.get("name"):
            data["name"] = params["name"]
        
        if params.get("description") is not None:
            data["description"] = params["description"]
        
        if params.get("table"):
            data["table"] = params["table"]
        
        if params.get("active") is not None:
            data["active"] = str(params["active"]).lower()
        
        if params.get("attributes"):
            # Add any additional attributes
            data.update(params["attributes"])
        
        if not data:
            return {"error": "No update parameters provided"}
        
        # Make the API request
        try:
            headers = auth_manager.get_headers()
            url = f"{server_config.instance_url}/api/now/table/wf_workflow/{workflow_id}"
            
            response = requests.patch(url, headers=headers, json=data)
            response.raise_for_status()
            
            result = response.json()
            return {
                "workflow": result.get("result", {}),
                "message": "Workflow updated successfully",
            }
        except requests.RequestException as e:
            logger.error(f"Error updating workflow: {e}")
            return {"error": str(e)}
        except Exception as e:
            logger.error(f"Unexpected error updating workflow: {e}")
            return {"error": str(e)}
  • Pydantic BaseModel defining the input schema for the update_workflow tool, with workflow_id required and other fields optional.
    class UpdateWorkflowParams(BaseModel):
        """Parameters for updating a workflow."""
        
        workflow_id: str = Field(..., description="Workflow ID or sys_id")
        name: Optional[str] = Field(None, description="Name of the workflow")
        description: Optional[str] = Field(None, description="Description of the workflow")
        table: Optional[str] = Field(None, description="Table the workflow applies to")
        active: Optional[bool] = Field(None, description="Whether the workflow is active")
        attributes: Optional[Dict[str, Any]] = Field(None, description="Additional attributes for the workflow")
  • Tool registration entry in get_tool_definitions() dict, specifying the aliased handler function, input schema model, input/return types, description, and serialization method for MCP server integration.
    "update_workflow": (
        update_workflow_tool,
        UpdateWorkflowParams,
        str,  # Expects JSON string
        "Update an existing workflow in ServiceNow",
        "json_dict",  # Tool returns Pydantic model
    ),
  • Helper function to unwrap and normalize input parameters, converting Pydantic models to dicts if necessary; used at line 536 in the handler.
    def _unwrap_params(params: Any, param_class: Type[T]) -> Dict[str, Any]:
        """
        Unwrap parameters if they're wrapped in a Pydantic model.
        This helps handle cases where the parameters are passed as a model instead of a dict.
        """
        if isinstance(params, dict):
            return params
        if isinstance(params, param_class):
            return params.dict(exclude_none=True)
        return params
  • Helper function to normalize auth_manager and server_config arguments, handling potential order swap; used in the handler.
    def _get_auth_and_config(
        auth_manager_or_config: Union[AuthManager, ServerConfig],
        server_config_or_auth: Union[ServerConfig, AuthManager],
    ) -> tuple[AuthManager, ServerConfig]:
        """
        Get the correct auth_manager and server_config objects.
        
        This function handles the case where the parameters might be swapped.
        
        Args:
            auth_manager_or_config: Either an AuthManager or a ServerConfig.
            server_config_or_auth: Either a ServerConfig or an AuthManager.
            
        Returns:
            tuple[AuthManager, ServerConfig]: The correct auth_manager and server_config.
            
        Raises:
            ValueError: If the parameters are not of the expected types.
        """
        # Check if the parameters are in the correct order
        if isinstance(auth_manager_or_config, AuthManager) and isinstance(server_config_or_auth, ServerConfig):
            return auth_manager_or_config, server_config_or_auth
        
        # Check if the parameters are swapped
        if isinstance(auth_manager_or_config, ServerConfig) and isinstance(server_config_or_auth, AuthManager):
            return server_config_or_auth, auth_manager_or_config
        
        # If we get here, at least one of the parameters is not of the expected type
        if hasattr(auth_manager_or_config, "get_headers"):
            auth_manager = auth_manager_or_config
        elif hasattr(server_config_or_auth, "get_headers"):
            auth_manager = server_config_or_auth
        else:
            raise ValueError("Cannot find get_headers method in either auth_manager or server_config")
        
        if hasattr(auth_manager_or_config, "instance_url"):
            server_config = auth_manager_or_config
        elif hasattr(server_config_or_auth, "instance_url"):
            server_config = server_config_or_auth
        else:
            raise ValueError("Cannot find instance_url attribute in either auth_manager or server_config")
        
        return auth_manager, server_config
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. While 'Update' implies a mutation operation, the description doesn't mention what permissions are required, whether changes are reversible, what happens to unspecified fields, or what the response looks like. This is a significant gap for a mutation tool with zero annotation coverage.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, efficient sentence that states exactly what the tool does without any wasted words. It's appropriately sized for a basic tool description and gets straight to the point.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a mutation tool with 6 parameters, no annotations, and no output schema, the description is inadequate. It doesn't explain what fields can be updated, what the workflow_id parameter represents, what happens during the update, or what the tool returns. The description should provide much more context given the tool's complexity and lack of structured documentation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The description provides zero information about parameters, while the schema has 6 parameters (workflow_id, active, attributes, description, name, table) with 0% schema description coverage. The description doesn't compensate for this complete lack of parameter documentation in the schema, leaving all parameters semantically undefined.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb ('Update') and resource ('an existing workflow in ServiceNow'), making the purpose immediately understandable. It doesn't differentiate from sibling tools like 'update_workflow_activity' or 'create_workflow', but it's specific enough to understand what the tool does.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives like 'create_workflow', 'deactivate_workflow', or 'update_workflow_activity'. There's no mention of prerequisites, constraints, or appropriate contexts for using this update operation.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Related Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/echelon-ai-labs/servicenow-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server