Skip to main content
Glama
vparlapalli490

ServiceNow MCP Server

create_knowledge_base

Create a new knowledge base in ServiceNow to organize and share information, specifying title, description, owner, and publication workflows.

Instructions

Create a new knowledge base in ServiceNow

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
titleYesTitle of the knowledge base
descriptionNoDescription of the knowledge base
ownerNoThe specified admin user or group
managersNoUsers who can manage this knowledge base
publish_workflowNoPublication workflowKnowledge - Instant Publish
retire_workflowNoRetirement workflowKnowledge - Instant Retire

Implementation Reference

  • The main handler function implementing the create_knowledge_base tool. It constructs a POST request to the ServiceNow kb_knowledge_base table with the provided parameters and returns a KnowledgeBaseResponse.
    def create_knowledge_base( config: ServerConfig, auth_manager: AuthManager, params: CreateKnowledgeBaseParams, ) -> KnowledgeBaseResponse: """ Create a new knowledge base in ServiceNow. Args: config: Server configuration. auth_manager: Authentication manager. params: Parameters for creating the knowledge base. Returns: Response with the created knowledge base details. """ api_url = f"{config.api_url}/table/kb_knowledge_base" # Build request data data = { "title": params.title, } if params.description: data["description"] = params.description if params.owner: data["owner"] = params.owner if params.managers: data["kb_managers"] = params.managers if params.publish_workflow: data["workflow_publish"] = params.publish_workflow if params.retire_workflow: data["workflow_retire"] = params.retire_workflow # 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", {}) return KnowledgeBaseResponse( success=True, message="Knowledge base created successfully", kb_id=result.get("sys_id"), kb_name=result.get("title"), ) except requests.RequestException as e: logger.error(f"Failed to create knowledge base: {e}") return KnowledgeBaseResponse( success=False, message=f"Failed to create knowledge base: {str(e)}", )
  • Pydantic BaseModel defining the input schema (parameters) for the create_knowledge_base tool, including title, description, owner, etc.
    class CreateKnowledgeBaseParams(BaseModel): """Parameters for creating a knowledge base.""" title: str = Field(..., description="Title of the knowledge base") description: Optional[str] = Field(None, description="Description of the knowledge base") owner: Optional[str] = Field(None, description="The specified admin user or group") managers: Optional[str] = Field(None, description="Users who can manage this knowledge base") publish_workflow: Optional[str] = Field("Knowledge - Instant Publish", description="Publication workflow") retire_workflow: Optional[str] = Field("Knowledge - Instant Retire", description="Retirement workflow")
  • Registration of the 'create_knowledge_base' tool in the tool_definitions dictionary used by the MCP server, mapping the name to its handler, schema, description, and serialization method.
    "create_knowledge_base": ( create_knowledge_base_tool, CreateKnowledgeBaseParams, str, # Expects JSON string "Create a new knowledge base in ServiceNow", "json_dict", # Tool returns Pydantic model ),
  • Import statement exposing create_knowledge_base from knowledge_base.py in the tools package __init__, making it available for import.
    from servicenow_mcp.tools.knowledge_base import ( create_article, create_category, create_knowledge_base, get_article, list_articles, list_knowledge_bases, publish_article, update_article, list_categories, )
  • Import of the handler function aliased as create_knowledge_base_tool for use in tool registration.
    # create_category aliased in function call create_knowledge_base as create_knowledge_base_tool, )

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/vparlapalli490/MCP'

If you have feedback or need assistance with the MCP directory API, please join our Discord server