Skip to main content
Glama
javerthl

ServiceNow MCP Server

by javerthl

create_workflow

Create new workflows in ServiceNow to automate business processes, define triggers, and manage task sequences for incident management, change requests, and service catalog operations.

Instructions

Create a new workflow in ServiceNow

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
activeNoWhether the workflow is active
attributesNoAdditional attributes for the workflow
descriptionNoDescription of the workflow
nameYesName of the workflow
tableNoTable the workflow applies to

Implementation Reference

  • The handler function that implements the create_workflow tool logic, unwrapping params, validating, preparing data, and POSTing to ServiceNow wf_workflow table API.
    def create_workflow(
        auth_manager: AuthManager,
        server_config: ServerConfig,
        params: Dict[str, Any],
    ) -> Dict[str, Any]:
        """
        Create a new workflow in ServiceNow.
        
        Args:
            auth_manager: Authentication manager
            server_config: Server configuration
            params: Parameters for creating a workflow
            
        Returns:
            Dict[str, Any]: Created workflow details
        """
        # Unwrap parameters if needed
        params = _unwrap_params(params, CreateWorkflowParams)
        
        # 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)}
        
        # Validate required parameters
        if not params.get("name"):
            return {"error": "Workflow name is required"}
        
        # Prepare data for the API request
        data = {
            "name": params["name"],
        }
        
        if params.get("description"):
            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"])
        
        # Make the API request
        try:
            headers = auth_manager.get_headers()
            url = f"{server_config.instance_url}/api/now/table/wf_workflow"
            
            response = requests.post(url, headers=headers, json=data)
            response.raise_for_status()
            
            result = response.json()
            return {
                "workflow": result.get("result", {}),
                "message": "Workflow created successfully",
            }
        except requests.RequestException as e:
            logger.error(f"Error creating workflow: {e}")
            return {"error": str(e)}
        except Exception as e:
            logger.error(f"Unexpected error creating workflow: {e}")
            return {"error": str(e)}
  • Pydantic model defining the input parameters for the create_workflow tool.
    class CreateWorkflowParams(BaseModel):
        """Parameters for creating a new workflow."""
        
        name: str = Field(..., 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(True, description="Whether the workflow is active")
        attributes: Optional[Dict[str, Any]] = Field(None, description="Additional attributes for the workflow")
  • MCP tool registration in get_tool_definitions dictionary, mapping 'create_workflow' to its handler alias, param schema, description, and serialization method.
    "create_workflow": (
        create_workflow_tool,
        CreateWorkflowParams,
        str,  # Expects JSON string
        "Create a new workflow in ServiceNow",
        "json_dict",  # Tool returns Pydantic model
    ),
  • Import of create_workflow (line 81) from workflow_tools.py into the tools package __init__, exposing it for use.
    from servicenow_mcp.tools.workflow_tools import (
        activate_workflow,
        add_workflow_activity,
        create_workflow,
        deactivate_workflow,
        delete_workflow_activity,
        get_workflow_activities,
        get_workflow_details,
        list_workflow_versions,
        list_workflows,
        reorder_workflow_activities,
        update_workflow,
        update_workflow_activity,
    )
  • Helper function used in create_workflow to unwrap Pydantic model parameters into a dict.
    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
Behavior2/5

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

With no annotations provided, the description carries full burden for behavioral disclosure. While 'Create' implies a write operation, it doesn't mention permission requirements, whether this is an idempotent operation, what happens on duplicate names, or what the response contains. For a creation tool with zero annotation coverage, this is inadequate.

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 with zero wasted words. It's appropriately sized for a basic creation operation and front-loads the essential information immediately.

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 creation tool with no annotations and no output schema, the description is insufficient. It doesn't explain what happens after creation, whether there are side effects, what permissions are needed, or how to verify success. Given the complexity of workflow creation in ServiceNow, more context is needed.

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

Parameters3/5

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

With 100% schema description coverage, the schema already documents all 5 parameters thoroughly. The description adds no additional parameter information beyond what's in the schema, so it meets the baseline expectation but doesn't provide extra value.

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 action ('Create') and resource ('new workflow in ServiceNow'), providing a specific verb+resource combination. However, it doesn't differentiate from sibling tools like 'update_workflow' or explain what distinguishes creation from other workflow operations.

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 'update_workflow', 'list_workflows', or 'get_workflow_details'. There's no mention of prerequisites, use cases, or when this tool would be inappropriate compared to sibling operations.

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

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/javerthl/servicenow-mcp'

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