Skip to main content
Glama
JurreBrandsenInfoSupport

Zendesk API MCP Server

create_article

Create new articles in Zendesk Guide by specifying title, content, section, and optional metadata like locale or labels.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
titleYesArticle title
bodyYesArticle body content (HTML)
section_idYesSection ID where the article will be created
localeNoArticle locale (e.g., 'en-us')
draftNoWhether the article is a draft
permission_group_idNoPermission group ID for the article
user_segment_idNoUser segment ID for the article
label_namesNoLabels for the article

Implementation Reference

  • The handler function for the 'create_article' tool. It constructs article data from inputs and calls the Zendesk client to create the article, returning success or error response.
    handler: async ({ title, body, section_id, locale, draft, permission_group_id, user_segment_id, label_names }) => {
      try {
        const articleData = {
          title,
          body,
          locale,
          draft,
          permission_group_id,
          user_segment_id,
          label_names
        };
        
        const result = await zendeskClient.createArticle(articleData, section_id);
        return {
          content: [{ 
            type: "text", 
            text: `Article created successfully!\n\n${JSON.stringify(result, null, 2)}`
          }]
        };
      } catch (error) {
        return {
          content: [{ type: "text", text: `Error creating article: ${error.message}` }],
          isError: true
        };
      }
  • Zod schema defining the input parameters and validation for the 'create_article' tool.
    schema: {
      title: z.string().describe("Article title"),
      body: z.string().describe("Article body content (HTML)"),
      section_id: z.number().describe("Section ID where the article will be created"),
      locale: z.string().optional().describe("Article locale (e.g., 'en-us')"),
      draft: z.boolean().optional().describe("Whether the article is a draft"),
      permission_group_id: z.number().optional().describe("Permission group ID for the article"),
      user_segment_id: z.number().optional().describe("User segment ID for the article"),
      label_names: z.array(z.string()).optional().describe("Labels for the article")
    },
  • The complete tool definition object for 'create_article', including name, description, schema, and handler, which is part of the helpCenterTools array exported and registered in the MCP server.
    {
      name: "create_article",
      description: "Create a new Help Center article",
      schema: {
        title: z.string().describe("Article title"),
        body: z.string().describe("Article body content (HTML)"),
        section_id: z.number().describe("Section ID where the article will be created"),
        locale: z.string().optional().describe("Article locale (e.g., 'en-us')"),
        draft: z.boolean().optional().describe("Whether the article is a draft"),
        permission_group_id: z.number().optional().describe("Permission group ID for the article"),
        user_segment_id: z.number().optional().describe("User segment ID for the article"),
        label_names: z.array(z.string()).optional().describe("Labels for the article")
      },
      handler: async ({ title, body, section_id, locale, draft, permission_group_id, user_segment_id, label_names }) => {
        try {
          const articleData = {
            title,
            body,
            locale,
            draft,
            permission_group_id,
            user_segment_id,
            label_names
          };
          
          const result = await zendeskClient.createArticle(articleData, section_id);
          return {
            content: [{ 
              type: "text", 
              text: `Article created successfully!\n\n${JSON.stringify(result, null, 2)}`
            }]
          };
        } catch (error) {
          return {
            content: [{ type: "text", text: `Error creating article: ${error.message}` }],
            isError: true
          };
        }
      }
  • Helper method in ZendeskClient that performs the actual API request to create an article in a specific section.
    async createArticle(data, sectionId) {
      return this.request(
        "POST",
        `/help_center/sections/${sectionId}/articles.json`,
        { article: data }
      );
Behavior1/5

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

Tool has no description.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness1/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Tool has no description.

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

Completeness1/5

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

Tool has no description.

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?

Tool has no description.

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

Purpose1/5

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

Tool has no description.

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?

Tool has no description.

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/JurreBrandsenInfoSupport/zendesk-mcp'

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