Skip to main content
Glama
echelon-ai-labs

ServiceNow MCP Server

create_category

Create a new category or subcategory in a ServiceNow knowledge base, including title, description, parent category, and activation status.

Instructions

Create a new category in a knowledge base

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
paramsYes

Implementation Reference

  • The core handler function that executes the create_category tool by making a POST request to ServiceNow's kb_category table with the provided parameters.
    def create_category(
        config: ServerConfig,
        auth_manager: AuthManager,
        params: CreateCategoryParams,
    ) -> CategoryResponse:
        """
        Create a new category in a knowledge base.
    
        Args:
            config: Server configuration.
            auth_manager: Authentication manager.
            params: Parameters for creating the category.
    
        Returns:
            Response with the created category details.
        """
        api_url = f"{config.api_url}/table/kb_category"
    
        # Build request data
        data = {
            "label": params.title,
            "kb_knowledge_base": params.knowledge_base,
            # Convert boolean to string "true"/"false" as ServiceNow expects
            "active": str(params.active).lower(),
        }
    
        if params.description:
            data["description"] = params.description
        if params.parent_category:
            data["parent"] = params.parent_category
        if params.parent_table:
            data["parent_table"] = params.parent_table
        
        # Log the request data for debugging
        logger.debug(f"Creating category with data: {data}")
    
        # 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", {})
            logger.debug(f"Category creation response: {result}")
    
            # Log the specific fields to check the knowledge base assignment
            if "kb_knowledge_base" in result:
                logger.debug(f"Knowledge base in response: {result['kb_knowledge_base']}")
            
            # Log the active status
            if "active" in result:
                logger.debug(f"Active status in response: {result['active']}")
            
            return CategoryResponse(
                success=True,
                message="Category created successfully",
                category_id=result.get("sys_id"),
                category_name=result.get("label"),
            )
    
        except requests.RequestException as e:
            logger.error(f"Failed to create category: {e}")
            return CategoryResponse(
                success=False,
                message=f"Failed to create category: {str(e)}",
            )
  • Pydantic BaseModel defining the input schema (parameters) for the create_category tool.
    class CreateCategoryParams(BaseModel):
        """Parameters for creating a category in a knowledge base."""
    
        title: str = Field(..., description="Title of the category")
        description: Optional[str] = Field(None, description="Description of the category")
        knowledge_base: str = Field(..., description="The knowledge base to create the category in")
        parent_category: Optional[str] = Field(None, description="Parent category (if creating a subcategory). Sys_id refering to the parent category or sys_id of the parent table.")
        parent_table: Optional[str] = Field(None, description="Parent table (if creating a subcategory). Sys_id refering to the table where the parent category is defined.")
        active: bool = Field(True, description="Whether the category is active")
  • Entry in the central tool_definitions dictionary that registers the create_category tool, specifying its handler implementation (aliased), input schema (aliased), return type hint, description, and serialization method.
    "create_category": (
        create_kb_category_tool_impl,  # Use passed function
        CreateKBCategoryParams,
        str,  # Expects JSON string
        "Create a new category in a knowledge base",
        "json_dict",  # Tool returns Pydantic model
    ),
  • Import of the create_category function aliased as create_kb_category_tool, which is passed to get_tool_definitions for tool registration.
        create_category as create_kb_category_tool,
    )
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 it's a creation operation but lacks details on permissions required, whether it's idempotent, error handling, or what happens on success (e.g., returns a category ID). This is a significant gap for a mutation tool with zero annotation coverage.

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 front-loads the core purpose without unnecessary words. Every part of the sentence earns its place by specifying the action, resource, and context.

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 (a mutation operation with 5 parameters), lack of annotations, and no output schema, the description is incomplete. It doesn't explain parameters, behavioral traits, or return values, making it inadequate for safe and effective tool invocation by an agent.

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?

The description provides no information about parameters, while the schema has 5 parameters (active, description, knowledge_base, parent_category, title) with 0% description coverage in the schema. This leaves all parameters undocumented, failing to compensate for the schema's lack of descriptions.

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 ('a new category in a knowledge base'), making the purpose immediately understandable. It distinguishes from siblings like 'create_catalog_category' by specifying the knowledge base context, though it doesn't explicitly contrast with 'list_categories' or other category-related tools.

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. The description doesn't mention prerequisites (e.g., needing an existing knowledge base), exclusions, or comparisons with sibling tools like 'list_categories' or 'create_catalog_category', leaving the agent without context for tool selection.

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