Skip to main content
Glama
javerthl

ServiceNow MCP Server

by javerthl

list_change_requests

Retrieve and filter change requests from ServiceNow to monitor and manage IT infrastructure modifications. Supports filtering by state, type, category, assignment group, and timeframe.

Instructions

List change requests from ServiceNow

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
assignment_groupNoFilter by assignment group
categoryNoFilter by category
limitNoMaximum number of records to return
offsetNoOffset to start from
queryNoAdditional query string
stateNoFilter by state
timeframeNoFilter by timeframe (upcoming, in-progress, completed)
typeNoFilter by type (normal, standard, emergency)

Implementation Reference

  • The handler function that executes the tool logic: validates params, builds ServiceNow query with filters, makes GET request to /api/now/table/change_request, returns list of change requests.
    def list_change_requests(
        auth_manager: AuthManager,
        server_config: ServerConfig,
        params: Dict[str, Any],
    ) -> Dict[str, Any]:
        """
        List change requests from ServiceNow.
    
        Args:
            auth_manager: The authentication manager.
            server_config: The server configuration.
            params: The parameters for listing change requests.
    
        Returns:
            A list of change requests.
        """
        # Unwrap and validate parameters
        result = _unwrap_and_validate_params(
            params, 
            ListChangeRequestsParams
        )
        
        if not result["success"]:
            return result
        
        validated_params = result["params"]
        
        # Build the query
        query_parts = []
        
        if validated_params.state:
            query_parts.append(f"state={validated_params.state}")
        if validated_params.type:
            query_parts.append(f"type={validated_params.type}")
        if validated_params.category:
            query_parts.append(f"category={validated_params.category}")
        if validated_params.assignment_group:
            query_parts.append(f"assignment_group={validated_params.assignment_group}")
        
        # Handle timeframe filtering
        if validated_params.timeframe:
            now = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
            if validated_params.timeframe == "upcoming":
                query_parts.append(f"start_date>{now}")
            elif validated_params.timeframe == "in-progress":
                query_parts.append(f"start_date<{now}^end_date>{now}")
            elif validated_params.timeframe == "completed":
                query_parts.append(f"end_date<{now}")
        
        # Add any additional query string
        if validated_params.query:
            query_parts.append(validated_params.query)
        
        # Combine query parts
        query = "^".join(query_parts) if query_parts else ""
        
        # 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",
            }
        
        # Make the API request
        url = f"{instance_url}/api/now/table/change_request"
        
        params = {
            "sysparm_limit": validated_params.limit,
            "sysparm_offset": validated_params.offset,
            "sysparm_query": query,
            "sysparm_display_value": "true",
        }
        
        try:
            response = requests.get(url, headers=headers, params=params)
            response.raise_for_status()
            
            result = response.json()
            
            # Handle the case where result["result"] is a list
            change_requests = result.get("result", [])
            count = len(change_requests)
            
            return {
                "success": True,
                "change_requests": change_requests,
                "count": count,
                "total": count,  # Use count as total if total is not provided
            }
        except requests.exceptions.RequestException as e:
            logger.error(f"Error listing change requests: {e}")
            return {
                "success": False,
                "message": f"Error listing change requests: {str(e)}",
            }
  • Pydantic BaseModel defining the input parameters for the list_change_requests tool, including pagination, filters, and custom query.
    class ListChangeRequestsParams(BaseModel):
        """Parameters for listing change requests."""
    
        limit: Optional[int] = Field(10, description="Maximum number of records to return")
        offset: Optional[int] = Field(0, description="Offset to start from")
        state: Optional[str] = Field(None, description="Filter by state")
        type: Optional[str] = Field(None, description="Filter by type (normal, standard, emergency)")
        category: Optional[str] = Field(None, description="Filter by category")
        assignment_group: Optional[str] = Field(None, description="Filter by assignment group")
        timeframe: Optional[str] = Field(None, description="Filter by timeframe (upcoming, in-progress, completed)")
        query: Optional[str] = Field(None, description="Additional query string")
  • Registers the tool in get_tool_definitions() with handler alias, schema, description, and JSON serialization for MCP server.
    "list_change_requests": (
        list_change_requests_tool,
        ListChangeRequestsParams,
        str,  # Expects JSON string
        "List change requests from ServiceNow",
        "json",  # Tool returns list/dict
    ),
  • Re-exports the list_change_requests function from change_tools for use in tool_utils.
    list_change_requests,
  • Helper function used by the handler to unwrap, validate input parameters against the Pydantic schema, and handle common input formats.
    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)}",
            }
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 but offers none. It doesn't mention that this is a read-only operation, doesn't describe pagination behavior (though limit/offset parameters exist), doesn't indicate authentication requirements, rate limits, or what format the results will be in. For a list operation with 8 parameters, this leaves significant behavioral questions unanswered.

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 maximally concise - a single sentence that states exactly what the tool does without any wasted words. It's front-loaded with the essential information and earns its place efficiently.

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 tool with 8 parameters, no annotations, and no output schema, the description is insufficiently complete. It doesn't explain what constitutes a 'change request' in ServiceNow context, doesn't describe the return format, and provides no behavioral context. While the schema covers parameter documentation, the overall tool understanding remains incomplete.

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?

The schema description coverage is 100%, so all parameters are documented in the schema itself. The description adds no additional parameter information beyond what's already in the structured schema fields. This meets the baseline expectation when the schema does the heavy lifting, 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 verb ('List') and resource ('change requests from ServiceNow'), making the purpose immediately understandable. However, it doesn't differentiate this tool from other list_* siblings like list_incidents or list_stories, which would require specifying what makes change requests distinct.

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. With many sibling tools available (including get_change_request_details for individual records and create_change_request for creation), there's no indication of when list_change_requests is appropriate versus other change-related tools.

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