Skip to main content
Glama
javerthl

ServiceNow MCP Server

by javerthl

create_change_request

Create a new change request in ServiceNow to manage IT infrastructure modifications, including type, risk, impact, and scheduling details for controlled implementation.

Instructions

Create a new change request in ServiceNow

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
assignment_groupNoGroup assigned to the change
categoryNoCategory of the change
descriptionNoDetailed description of the change request
end_dateNoPlanned end date (YYYY-MM-DD HH:MM:SS)
impactNoImpact of the change
requested_byNoUser who requested the change
riskNoRisk level of the change
short_descriptionYesShort description of the change request
start_dateNoPlanned start date (YYYY-MM-DD HH:MM:SS)
typeYesType of change (normal, standard, emergency)

Implementation Reference

  • The main handler function that executes the create_change_request tool. It validates input parameters using Pydantic, prepares the data, makes a POST request to ServiceNow's change_request table API, and returns the result.
    def create_change_request(
        auth_manager: AuthManager,
        server_config: ServerConfig,
        params: Dict[str, Any],
    ) -> Dict[str, Any]:
        """
        Create a new change request in ServiceNow.
    
        Args:
            auth_manager: The authentication manager.
            server_config: The server configuration.
            params: The parameters for creating the change request.
    
        Returns:
            The created change request.
        """
        # Unwrap and validate parameters
        result = _unwrap_and_validate_params(
            params, 
            CreateChangeRequestParams, 
            required_fields=["short_description", "type"]
        )
        
        if not result["success"]:
            return result
        
        validated_params = result["params"]
        
        # Prepare the request data
        data = {
            "short_description": validated_params.short_description,
            "type": validated_params.type,
        }
        
        # Add optional fields if provided
        if validated_params.description:
            data["description"] = validated_params.description
        if validated_params.risk:
            data["risk"] = validated_params.risk
        if validated_params.impact:
            data["impact"] = validated_params.impact
        if validated_params.category:
            data["category"] = validated_params.category
        if validated_params.requested_by:
            data["requested_by"] = validated_params.requested_by
        if validated_params.assignment_group:
            data["assignment_group"] = validated_params.assignment_group
        if validated_params.start_date:
            data["start_date"] = validated_params.start_date
        if validated_params.end_date:
            data["end_date"] = validated_params.end_date
        
        # 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",
            }
        
        # Add Content-Type header
        headers["Content-Type"] = "application/json"
        
        # Make the API request
        url = f"{instance_url}/api/now/table/change_request"
        
        try:
            response = requests.post(url, json=data, headers=headers)
            response.raise_for_status()
            
            result = response.json()
            
            return {
                "success": True,
                "message": "Change request created successfully",
                "change_request": result["result"],
            }
        except requests.exceptions.RequestException as e:
            logger.error(f"Error creating change request: {e}")
            return {
                "success": False,
                "message": f"Error creating change request: {str(e)}",
            }
  • Pydantic BaseModel defining the input schema for the create_change_request tool, including required fields like short_description and type, and optional fields like risk, impact, etc.
    class CreateChangeRequestParams(BaseModel):
        """Parameters for creating a change request."""
    
        short_description: str = Field(..., description="Short description of the change request")
        description: Optional[str] = Field(None, description="Detailed description of the change request")
        type: str = Field(..., description="Type of change (normal, standard, emergency)")
        risk: Optional[str] = Field(None, description="Risk level of the change")
        impact: Optional[str] = Field(None, description="Impact of the change")
        category: Optional[str] = Field(None, description="Category of the change")
        requested_by: Optional[str] = Field(None, description="User who requested the change")
        assignment_group: Optional[str] = Field(None, description="Group assigned to the change")
        start_date: Optional[str] = Field(None, description="Planned start date (YYYY-MM-DD HH:MM:SS)")
        end_date: Optional[str] = Field(None, description="Planned end date (YYYY-MM-DD HH:MM:SS)")
  • Tool registration entry in the get_tool_definitions dictionary. Maps the tool name to its implementation function (aliased), input schema, return type hint, description, and serialization method.
    "create_change_request": (
        create_change_request_tool,
        CreateChangeRequestParams,
        str,
        "Create a new change request in ServiceNow",
        "str",
    ),
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. It states the tool creates a change request but doesn't describe what happens after creation (e.g., whether it triggers workflows, sends notifications, or returns an ID), potential side effects, error conditions, or authentication requirements. For a mutation tool with zero annotation coverage, this leaves significant gaps in understanding its behavior.

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, direct sentence with zero wasted words. It front-loads the core purpose ('Create a new change request') and specifies the system ('in ServiceNow'), making it immediately clear and efficient. Every word earns its place.

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?

Given the complexity of creating a change request (10 parameters, 2 required), no annotations, and no output schema, the description is insufficient. It doesn't explain what the tool returns (e.g., a change request ID or confirmation), error handling, or system-specific constraints (e.g., ServiceNow field validations). For a mutation tool in a workflow-heavy context, this leaves the agent under-informed.

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?

Schema description coverage is 100%, so the schema already documents all 10 parameters with titles and descriptions. The description adds no parameter-specific information beyond what's in the schema, such as explaining relationships between parameters (e.g., how 'type' affects other fields) or providing examples. The baseline score of 3 reflects adequate coverage from the schema alone.

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 change request in ServiceNow'), making the purpose immediately understandable. It distinguishes from siblings like 'update_change_request' by specifying creation rather than modification, though it doesn't explicitly contrast with other creation tools like 'create_incident' or 'create_project'.

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. It doesn't mention prerequisites (e.g., required permissions), when to choose this over similar creation tools (e.g., 'create_incident'), or what constitutes a valid change request scenario. The agent must infer usage from the tool name alone.

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