Skip to main content
Glama
echelon-ai-labs

ServiceNow MCP Server

list_changesets

Retrieve and filter changesets in ServiceNow by application, developer, state, timeframe, or custom queries using the MCP server. Streamline tracking and management of changes.

Instructions

List changesets from ServiceNow

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
paramsYes

Implementation Reference

  • The core handler function for the 'list_changesets' tool. Validates parameters, builds ServiceNow API query for sys_update_set table, fetches and returns list of changesets.
    def list_changesets(
        auth_manager: AuthManager,
        server_config: ServerConfig,
        params: Union[Dict[str, Any], ListChangesetsParams],
    ) -> Dict[str, Any]:
        """
        List changesets from ServiceNow.
    
        Args:
            auth_manager: The authentication manager.
            server_config: The server configuration.
            params: The parameters for listing changesets. Can be a dictionary or a ListChangesetsParams object.
    
        Returns:
            A list of changesets.
        """
        # Unwrap and validate parameters
        result = _unwrap_and_validate_params(params, ListChangesetsParams)
        
        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",
            }
        
        # Build query parameters
        query_params = {
            "sysparm_limit": validated_params.limit,
            "sysparm_offset": validated_params.offset,
        }
        
        # Build sysparm_query
        query_parts = []
        
        if validated_params.state:
            query_parts.append(f"state={validated_params.state}")
        
        if validated_params.application:
            query_parts.append(f"application={validated_params.application}")
        
        if validated_params.developer:
            query_parts.append(f"developer={validated_params.developer}")
        
        if validated_params.timeframe:
            if validated_params.timeframe == "recent":
                query_parts.append("sys_created_onONLast 7 days@javascript:gs.beginningOfLast7Days()@javascript:gs.endOfToday()")
            elif validated_params.timeframe == "last_week":
                query_parts.append("sys_created_onONLast week@javascript:gs.beginningOfLastWeek()@javascript:gs.endOfLastWeek()")
            elif validated_params.timeframe == "last_month":
                query_parts.append("sys_created_onONLast month@javascript:gs.beginningOfLastMonth()@javascript:gs.endOfLastMonth()")
        
        if validated_params.query:
            query_parts.append(validated_params.query)
        
        if query_parts:
            query_params["sysparm_query"] = "^".join(query_parts)
        
        # Make the API request
        url = f"{instance_url}/api/now/table/sys_update_set"
        
        try:
            response = requests.get(url, params=query_params, headers=headers)
            response.raise_for_status()
            
            result = response.json()
            
            return {
                "success": True,
                "changesets": result.get("result", []),
                "count": len(result.get("result", [])),
            }
        except requests.exceptions.RequestException as e:
            logger.error(f"Error listing changesets: {e}")
            return {
                "success": False,
                "message": f"Error listing changesets: {str(e)}",
            }
  • Pydantic BaseModel defining the input schema/parameters for the list_changesets tool.
    class ListChangesetsParams(BaseModel):
        """Parameters for listing changesets."""
    
        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")
        application: Optional[str] = Field(None, description="Filter by application")
        developer: Optional[str] = Field(None, description="Filter by developer")
        timeframe: Optional[str] = Field(None, description="Filter by timeframe (recent, last_week, last_month)")
        query: Optional[str] = Field(None, description="Additional query string")
  • MCP tool registration in get_tool_definitions() dict: maps name to (handler_func, params_model, return_type, description, serialization_hint). Used by server to expose the tool schema and call handler.
    "list_changesets": (
        list_changesets_tool,
        ListChangesetsParams,
        str,  # Expects JSON string
        "List changesets from ServiceNow",
        "json",  # Tool returns list/dict
    ),
  • Shared helper function used by list_changesets (and other tools) to validate and parse input params against the Pydantic schema.
    def _unwrap_and_validate_params(
        params: Union[Dict[str, Any], BaseModel], 
        model_class: Type[T], 
        required_fields: Optional[List[str]] = None
    ) -> Dict[str, Any]:
        """
        Unwrap and validate parameters.
    
        Args:
            params: The parameters to unwrap and validate. Can be a dictionary or a Pydantic model.
            model_class: The Pydantic model class to validate against.
            required_fields: List of fields that must be present.
    
        Returns:
            A dictionary with success status and validated parameters or error message.
        """
        try:
            # Handle case where params is already a Pydantic model
            if isinstance(params, BaseModel):
                # If it's already the correct model class, use it directly
                if isinstance(params, model_class):
                    model_instance = params
                # Otherwise, convert to dict and create new instance
                else:
                    model_instance = model_class(**params.dict())
            # Handle dictionary case
            else:
                # Create model instance
                model_instance = model_class(**params)
            
            # Check required fields
            if required_fields:
                missing_fields = []
                for field in required_fields:
                    if getattr(model_instance, field, None) is None:
                        missing_fields.append(field)
                
                if missing_fields:
                    return {
                        "success": False,
                        "message": f"Missing required fields: {', '.join(missing_fields)}",
                    }
            
            return {
                "success": True,
                "params": model_instance,
            }
        except Exception as e:
            return {
                "success": False,
                "message": f"Invalid parameters: {str(e)}",
            }
  • Helper to retrieve auth headers, flexible to arg order (auth_manager or server_config first). Used in list_changesets API call.
    def _get_headers(auth_manager: AuthManager, server_config: ServerConfig) -> Optional[Dict[str, str]]:
        """
        Get the headers from either auth_manager or server_config.
    
        Args:
            auth_manager: The authentication manager.
            server_config: The server configuration.
    
        Returns:
            The headers or None if not found.
        """
        # Try to get headers from auth_manager
        if hasattr(auth_manager, 'get_headers'):
            return auth_manager.get_headers()
        
        # Try to get headers from server_config
        if hasattr(server_config, 'get_headers'):
            return server_config.get_headers()
        
        # If neither has get_headers, check if auth_manager is actually a ServerConfig
        # and server_config is actually an AuthManager (parameters swapped)
        if hasattr(server_config, 'get_headers') and not hasattr(auth_manager, 'get_headers'):
            return server_config.get_headers()
        
        logger.error("Cannot find get_headers method in either auth_manager or server_config")
        return None
Behavior2/5

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

No annotations are provided, so the description carries full burden. It mentions 'List' which implies a read operation, but doesn't disclose behavioral traits like whether it's paginated, rate-limited, requires authentication, returns partial/full data, or how results are ordered. For a list operation with 7 parameters, this leaves significant gaps.

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 extremely concise at just 4 words, with zero wasted language. It's front-loaded with the core action and resource, though this brevity comes at the cost of completeness.

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 tool's complexity (7 parameters, no output schema, no annotations), the description is severely incomplete. It doesn't explain what a changeset is in this context, how results are returned, what filtering options exist, or any behavioral characteristics. The agent would struggle to use this tool effectively.

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?

Schema description coverage is 0%, meaning none of the 7 parameters are documented in the schema. The description provides no information about any parameters, failing to compensate for the complete lack of schema documentation. This leaves the agent with no guidance on what 'application', 'developer', 'timeframe', etc. mean.

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

Purpose3/5

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

The description 'List changesets from ServiceNow' states the basic action (list) and resource (changesets), but is vague about scope and lacks differentiation from sibling tools like 'list_change_requests' or 'get_changeset_details'. It doesn't specify whether this lists all changesets, filtered ones, or provides pagination details.

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?

No guidance is provided on when to use this tool versus alternatives. With siblings like 'get_changeset_details' (for specific changesets) and 'list_change_requests' (for related entities), the description offers no context on appropriate use cases, prerequisites, or distinctions.

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