Skip to main content
Glama
javerthl

ServiceNow MCP Server

by javerthl

create_group

Create a new group in ServiceNow with configurable parameters including name, description, manager, parent group, type, email, members, and active status.

Instructions

Create a new group in ServiceNow

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
activeNoWhether the group is active
descriptionNoDescription of the group
emailNoEmail address for the group
managerNoManager of the group (sys_id or username)
membersNoList of user sys_ids or usernames to add as members
nameYesName of the group
parentNoParent group (sys_id or name)
typeNoType of the group

Implementation Reference

  • The main handler function that executes the create_group tool logic: posts to ServiceNow's sys_user_group table API, builds payload from params, handles optional fields, adds members post-creation if specified, returns GroupResponse.
    def create_group(
        config: ServerConfig,
        auth_manager: AuthManager,
        params: CreateGroupParams,
    ) -> GroupResponse:
        """
        Create a new group in ServiceNow.
    
        Args:
            config: Server configuration.
            auth_manager: Authentication manager.
            params: Parameters for creating the group.
    
        Returns:
            Response with the created group details.
        """
        api_url = f"{config.api_url}/table/sys_user_group"
    
        # Build request data
        data = {
            "name": params.name,
            "active": str(params.active).lower(),
        }
    
        if params.description:
            data["description"] = params.description
        if params.manager:
            data["manager"] = params.manager
        if params.parent:
            data["parent"] = params.parent
        if params.type:
            data["type"] = params.type
        if params.email:
            data["email"] = params.email
    
        # Make request
        try:
            response = requests.post(
                api_url,
                json=data,
                headers=auth_manager.get_headers(),
                timeout=config.timeout,
            )
            response.raise_for_status()
    
            result = response.json().get("result", {})
            group_id = result.get("sys_id")
    
            # Add members if provided
            if params.members and group_id:
                add_group_members(
                    config,
                    auth_manager,
                    AddGroupMembersParams(group_id=group_id, members=params.members),
                )
    
            return GroupResponse(
                success=True,
                message="Group created successfully",
                group_id=group_id,
                group_name=result.get("name"),
            )
    
        except requests.RequestException as e:
            logger.error(f"Failed to create group: {e}")
            return GroupResponse(
                success=False,
                message=f"Failed to create group: {str(e)}",
            )
  • Pydantic BaseModel defining the input schema (parameters) for the create_group tool, with validation and descriptions for MCP tool schema.
    class CreateGroupParams(BaseModel):
        """Parameters for creating a group."""
    
        name: str = Field(..., description="Name of the group")
        description: Optional[str] = Field(None, description="Description of the group")
        manager: Optional[str] = Field(None, description="Manager of the group (sys_id or username)")
        parent: Optional[str] = Field(None, description="Parent group (sys_id or name)")
        type: Optional[str] = Field(None, description="Type of the group")
        email: Optional[str] = Field(None, description="Email address for the group")
        members: Optional[List[str]] = Field(
            None, description="List of user sys_ids or usernames to add as members"
        )
        active: Optional[bool] = Field(True, description="Whether the group is active")
  • Tool registration in the central tool_definitions dictionary used by the MCP server: maps 'create_group' to its aliased handler, schema, return type hint, description, and serialization handling.
    "create_group": (
        create_group_tool,
        CreateGroupParams,
        Dict[str, Any],  # Expects dict
        "Create a new group in ServiceNow",
        "raw_dict",
    ),
  • Re-export of create_group from user_tools.py in the tools package __init__.py for convenient imports.
    from servicenow_mcp.tools.user_tools import (
        create_user,
        update_user,
        get_user,
        list_users,
        create_group,
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 only states it 'creates' without additional context. It doesn't mention permissions required, whether the operation is idempotent, what happens on failure, or what the return value might be (especially problematic since there's no output schema). For a mutation 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 that states the core purpose without any fluff. It's appropriately sized and front-loaded, making it easy for an agent to parse quickly.

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 8 parameters, no annotations, and no output schema, the description is insufficiently complete. It doesn't address behavioral aspects (permissions, side effects), provide usage context, or hint at return values. The agent lacks critical information needed to use this tool effectively beyond basic parameter documentation.

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 all 8 parameters are well-documented in the schema itself. The description adds no parameter-specific information beyond what's already in the schema (like explaining format constraints or relationships between parameters). Baseline 3 is appropriate when the schema does all the work.

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 group in ServiceNow'), making the purpose immediately understandable. However, it doesn't differentiate this tool from other 'create' tools in the sibling list like create_user, create_incident, or create_change_request, which would require a 5.

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. There's no mention of prerequisites, when not to use it, or how it relates to sibling tools like update_group, add_group_members, or list_groups. The agent must infer usage from context 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