Skip to main content
Glama
JLKmach

ServiceNow MCP Server

by JLKmach

get_article

Retrieve a specific knowledge article from ServiceNow by providing its unique article ID to access documented solutions and information.

Instructions

Get a specific knowledge article by ID

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
article_idYesID of the article to get

Implementation Reference

  • The handler function that implements the get_article tool logic by fetching the article from the ServiceNow API and formatting the response.
    def get_article(
        config: ServerConfig,
        auth_manager: AuthManager,
        params: GetArticleParams,
    ) -> Dict[str, Any]:
        """
        Get a specific knowledge article by ID.
    
        Args:
            config: Server configuration.
            auth_manager: Authentication manager.
            params: Parameters for getting the article.
    
        Returns:
            Dictionary with article details.
        """
        api_url = f"{config.api_url}/table/kb_knowledge/{params.article_id}"
    
        # Build query parameters
        query_params = {
            "sysparm_display_value": "true",
        }
    
        # 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()
            
            # 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": "Unexpected response format",
                }
    
            if not result or not isinstance(result, dict):
                return {
                    "success": False,
                    "message": f"Article with ID {params.article_id} not found",
                }
    
            # Extract values safely
            article_id = result.get("sys_id", "")
            title = result.get("short_description", "")
            text = result.get("text", "")
            
            # Extract nested values safely
            knowledge_base = ""
            if isinstance(result.get("kb_knowledge_base"), dict):
                knowledge_base = result["kb_knowledge_base"].get("display_value", "")
            
            category = ""
            if isinstance(result.get("kb_category"), dict):
                category = result["kb_category"].get("display_value", "")
            
            workflow_state = ""
            if isinstance(result.get("workflow_state"), dict):
                workflow_state = result["workflow_state"].get("display_value", "")
            
            author = ""
            if isinstance(result.get("author"), dict):
                author = result["author"].get("display_value", "")
            
            keywords = result.get("keywords", "")
            article_type = result.get("article_type", "")
            views = result.get("view_count", "0")
            created = result.get("sys_created_on", "")
            updated = result.get("sys_updated_on", "")
    
            article = {
                "id": article_id,
                "title": title,
                "text": text,
                "knowledge_base": knowledge_base,
                "category": category,
                "workflow_state": workflow_state,
                "created": created,
                "updated": updated,
                "author": author,
                "keywords": keywords,
                "article_type": article_type,
                "views": views,
            }
    
            return {
                "success": True,
                "message": "Article retrieved successfully",
                "article": article,
            }
    
        except requests.RequestException as e:
            logger.error(f"Failed to get article: {e}")
            return {
                "success": False,
                "message": f"Failed to get article: {str(e)}",
            }
  • Pydantic model defining the input parameters for the get_article tool, requiring the article_id.
    class GetArticleParams(BaseModel):
        """Parameters for getting a knowledge article."""
    
        article_id: str = Field(..., description="ID of the article to get")
  • Registration of the get_article tool in the central tool definitions dictionary, specifying the handler function alias, input schema, return type hint, description, and serialization method.
    "get_article": (
        get_article_tool,
        GetArticleParams,
        Dict[str, Any],  # Expects dict
        "Get a specific knowledge article by ID",
        "raw_dict",  # Tool returns raw dict
    ),
  • Import of the get_article handler from knowledge_base.py into the tools package __init__, making it available for export.
    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,
    )

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

B3.1/5.0
Behavior2/5

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. While 'Get' implies a read operation, the description doesn't mention authentication requirements, rate limits, error conditions, or what happens if the article ID doesn't exist. For a tool with zero annotation coverage, this leaves significant behavioral 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 a single, efficient sentence that gets straight to the point with zero wasted words. It's appropriately sized for a simple retrieval tool and front-loads the essential information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple retrieval tool with one parameter and no output schema, the description is minimally adequate but has clear gaps. It doesn't explain what information is returned, how to handle errors, or how this differs from related tools. With no annotations and no output schema, more context about the return format would be helpful.

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 description mentions 'by ID' which aligns with the single 'article_id' parameter in the schema. Since schema description coverage is 100% (the parameter is fully documented in the schema), the description adds minimal value beyond what's already in structured data. This meets the baseline expectation when schema coverage is high.

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 verb ('Get') and resource ('a specific knowledge article by ID'), making the purpose immediately understandable. However, it doesn't distinguish this tool from its sibling 'list_articles' or explain how this differs from other retrieval tools like 'get_catalog_item' or 'get_user'.

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. It doesn't mention that 'list_articles' exists for browsing articles or explain when you need a specific article ID versus listing articles. There's no context about prerequisites or typical use cases.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools