Skip to main content
Glama
javerthl

ServiceNow MCP Server

by javerthl

list_articles

Retrieve knowledge articles from ServiceNow with filtering options for knowledge base, category, search query, and workflow state to find relevant information.

Instructions

List knowledge articles

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
categoryNoFilter by category
knowledge_baseNoFilter by knowledge base
limitNoMaximum number of articles to return
offsetNoOffset for pagination
queryNoSearch query for articles
workflow_stateNoFilter by workflow state

Implementation Reference

  • The core handler function that executes the list_articles tool by querying the ServiceNow kb_knowledge table API with filters and returning formatted article list.
    def list_articles(
        config: ServerConfig,
        auth_manager: AuthManager,
        params: ListArticlesParams,
    ) -> Dict[str, Any]:
        """
        List knowledge articles with filtering options.
    
        Args:
            config: Server configuration.
            auth_manager: Authentication manager.
            params: Parameters for listing articles.
    
        Returns:
            Dictionary with list of articles and metadata.
        """
        api_url = f"{config.api_url}/table/kb_knowledge"
    
        # Build query parameters
        query_params = {
            "sysparm_limit": params.limit,
            "sysparm_offset": params.offset,
            "sysparm_display_value": "all",
        }
    
        # Build query string
        query_parts = []
        if params.knowledge_base:
            query_parts.append(f"kb_knowledge_base.sys_id={params.knowledge_base}")
        if params.category:
            query_parts.append(f"kb_category.sys_id={params.category}")
        if params.workflow_state:
            query_parts.append(f"workflow_state={params.workflow_state}")
        if params.query:
            query_parts.append(f"short_descriptionLIKE{params.query}^ORtextLIKE{params.query}")
    
        if query_parts:
            query_string = "^".join(query_parts)
            logger.debug(f"Constructed article query string: {query_string}")
            query_params["sysparm_query"] = query_string
        
        # Log the query parameters for debugging
        logger.debug(f"Listing articles with query params: {query_params}")
    
        # Make request
        try:
            response = requests.get(
                api_url,
                params=query_params,
                headers=auth_manager.get_headers(),
                timeout=config.timeout,
            )
            response.raise_for_status()
    
            # Get the JSON response
            json_response = response.json()
            logger.debug(f"Article listing raw response: {json_response}")
            
            # Safely extract the result
            if isinstance(json_response, dict) and "result" in json_response:
                result = json_response.get("result", [])
            else:
                logger.error("Unexpected response format: %s", json_response)
                return {
                    "success": False,
                    "message": f"Unexpected response format",
                    "articles": [],
                    "count": 0,
                    "limit": params.limit,
                    "offset": params.offset,
                }
    
            # Transform the results
            articles = []
            
            # Handle either string or list
            if isinstance(result, list):
                for article_item in result:
                    if not isinstance(article_item, dict):
                        logger.warning("Skipping non-dictionary article item: %s", article_item)
                        continue
                        
                    # Safely extract values
                    article_id = article_item.get("sys_id", "")
                    title = article_item.get("short_description", "")
                    
                    # Extract nested values safely
                    knowledge_base = ""
                    if isinstance(article_item.get("kb_knowledge_base"), dict):
                        knowledge_base = article_item["kb_knowledge_base"].get("display_value", "")
                    
                    category = ""
                    if isinstance(article_item.get("kb_category"), dict):
                        category = article_item["kb_category"].get("display_value", "")
                    
                    workflow_state = ""
                    if isinstance(article_item.get("workflow_state"), dict):
                        workflow_state = article_item["workflow_state"].get("display_value", "")
                    
                    created = article_item.get("sys_created_on", "")
                    updated = article_item.get("sys_updated_on", "")
                    
                    articles.append({
                        "id": article_id,
                        "title": title,
                        "knowledge_base": knowledge_base,
                        "category": category,
                        "workflow_state": workflow_state,
                        "created": created,
                        "updated": updated,
                    })
            else:
                logger.warning("Result is not a list: %s", result)
    
            return {
                "success": True,
                "message": f"Found {len(articles)} articles",
                "articles": articles,
                "count": len(articles),
                "limit": params.limit,
                "offset": params.offset,
            }
    
        except requests.RequestException as e:
            logger.error(f"Failed to list articles: {e}")
            return {
                "success": False,
                "message": f"Failed to list articles: {str(e)}",
                "articles": [],
                "count": 0,
                "limit": params.limit,
                "offset": params.offset,
            }
  • Pydantic BaseModel defining the input parameters (limit, offset, filters) for the list_articles tool.
    class ListArticlesParams(BaseModel):
        """Parameters for listing knowledge articles."""
        
        limit: int = Field(10, description="Maximum number of articles to return")
        offset: int = Field(0, description="Offset for pagination")
        knowledge_base: Optional[str] = Field(None, description="Filter by knowledge base")
        category: Optional[str] = Field(None, description="Filter by category")
        query: Optional[str] = Field(None, description="Search query for articles")
        workflow_state: Optional[str] = Field(None, description="Filter by workflow state")
  • Registers the list_articles tool in the MCP tool definitions dictionary, linking the handler function, input schema, return type, description, and serialization method.
    "list_articles": (
        list_articles_tool,
        ListArticlesParams,
        Dict[str, Any],  # Expects dict
        "List knowledge articles",
        "raw_dict",  # Tool returns raw dict
    ),
  • Includes list_articles in the __all__ export list for the tools module.
    "list_articles",
  • Imports the list_articles handler as list_articles_tool for use in tool registration.
    list_articles as list_articles_tool,
Behavior2/5

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

With no annotations provided, the description carries the full burden of behavioral disclosure but offers almost none. 'List knowledge articles' implies a read-only operation but doesn't specify pagination behavior, rate limits, authentication requirements, or what happens when filters return no results. The description fails to provide meaningful behavioral context beyond the basic operation implied by the name.

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 at just three words with zero wasted language. It's appropriately sized for such a simple statement, though this conciseness comes at the expense of providing helpful information beyond the tool name.

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 list tool with 6 parameters, no annotations, and no output schema, the description is inadequate. While the schema covers parameters well, the description fails to provide necessary context about the tool's behavior, return format, or relationship to other tools. The agent would need to infer too much from just 'List knowledge articles' given the tool's complexity.

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%, with all 6 parameters well-documented in the schema itself. The description adds no additional parameter information beyond what's already in the schema. According to the scoring rules, when schema coverage is high (>80%), the baseline score is 3 even with no parameter information in the description.

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

Purpose2/5

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

The description 'List knowledge articles' is a tautology that merely restates the tool name 'list_articles' with minimal added context. It specifies the resource ('knowledge articles') but lacks a clear verb beyond 'list' and doesn't differentiate from sibling tools like 'get_article' or 'create_article' beyond the obvious list vs. get/create distinction.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines1/5

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 when to use 'list_articles' versus 'get_article' for retrieving specific articles, or how it relates to other list tools like 'list_knowledge_bases'. The agent receives no contextual usage information.

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