Connect your AI Agents to Zendesk in minutes

What is a Zendesk MCP server?

It’s an MCP server that exposes data and functionality from Zendesk via tools. Your agents can use these tools to do everything from updating a support ticket to removing a user in your Zendesk instance.

How can I use the Zendesk MCP server?

Here are just a few ways to use it:

• Automated ticket triage and routing: Your agent can classify incoming tickets by intent, priority, or customer tier and route them to the right team. For example, enterprise billing issues can be auto-escalated to a high-priority queue

• AI-assisted ticket responses: Your agent can draft replies using ticket history, macros, and help center content. For example, common integration issues can trigger pre-filled troubleshooting responses for quick resolution

• Customer context enrichment: Your agent can enrich tickets with CRM, billing, or product usage data. For example, account plan, ARR, and recent activity can be surfaced directly on each ticket

• Proactive issue detection: Your agent can detect spikes or patterns across tickets to identify emerging issues. For example, repeated API error reports can trigger alerts and incident creation

• Cross-tool workflow automation: Your agent can trigger actions in other systems from Zendesk events. For example, confirming a bug can automatically create a Jira issue, notify Slack, and update the customer

What are popular tools for Zendesk’s MCP server?

Here are some popular tools across data types:

Organizations

• <code class="blog_inline-code">get_organization</code>
• <code class="blog_inline-code">list_organization</code>
• <code class="blog_inline-code">create_organization</code>
• <code class="blog_inline-code">get_organization_tickets</code>

Tickets

• <code class="blog_inline-code">list_tickets</code>
• <code class="blog_inline-code">get_ticket</code>
• <code class="blog_inline-code">update_ticket</code>
• <code class="blog_inline-code">get_tickets_comments</code>

Users

• <code class="blog_inline-code">list_users</code>
• <code class="blog_inline-code">suspend_user</code>
• <code class="blog_inline-code">search_users</code>
• <code class="blog_inline-code">delete_user</code>

What makes Merge Agent Handler’s Zendesk MCP server better than alternative Zendesk MCP servers?

Merge Agent Handler’s Zendesk MCP server comes with platform-level capabilities:

• Enterprise-grade security and DLP: All Zendesk tool inputs and outputs pass through Merge’s Security Gateway, which can block, redact, or mask sensitive data using default or custom rules. This applies consistently across all connectors, including Zendesk
  

• Centralized authentication and credential management: Merge handles individual or shared authentication for Zendesk connectors, removing the need to manage OAuth flows or credentials inside agent code
  

• Real-time observability with a complete audit trail: Every Zendesk tool call is logged, including underlying API requests. Logs are fully searchable, enabling auditing, debugging, and behavioral analysis across agents and users
  

• Evaluation Suite for quality assurance: Test and validate Zendesk tool calls across different prompts before deploying to production. This ensures high-quality, consistent tool performance and helps optimize outputs for reliability

Can I set custom security rules for Zendesk tool calls in Merge Agent Handler?

Yes, Merge Agent Handler supports custom security rules through its Security Gateway and Data Loss Protection (DLP) system. These rules can inspect both tool inputs and outputs and automatically block, redact, or mask sensitive data before it is returned to the agent.

Here are just a few examples:

• Customer email addresses and phone numbers: Block or redact any tool calls that attempt to include customer contact information in ticket comments, internal notes, or agent responses

• Credit card numbers: Automatically block any attempts to include credit card information in Zendesk tickets, comments, or custom fields before they're written to your support platform
  

• Social security numbers: Block any tool calls that attempt to include SSNs in ticket descriptions, comments, or custom field values
  

• Internal account IDs: Mask sensitive customer identifiers when agents read or update Zendesk tickets to prevent cross-account information leakage
  

• API keys and tokens: Block any tool calls that attempt to include API keys, authentication tokens, or credentials in ticket content or metadata
  

• External webhook destinations: Block tool calls that attempt to configure Zendesk triggers or webhooks with destinations outside your organization's approved domains

How can I start using Merge Agent Handler’s Zendesk MCP server?

You can follow these steps:

1. Create your Agent Handler account. Sign up for a free account.

2. Create a Tool Pack. Navigate to "Tool Packs" in the left sidebar and click "Create New Tool Pack." Give it a descriptive name (e.g., "Zendesk Support Pack").

3. Add the Zendesk connector. In your Tool Pack settings, click "Add Connector" and select Zendesk from the connector marketplace.

4. Authenticate with Zendesk. Click the authentication button to connect your Zendesk account via OAuth. You can configure this as individual authentication (each user connects their own Zendesk account) or shared authentication (one admin connection for all users).

5. Select specific tools. Choose which Zendesk tools you want to make available to your agent, or enable all tools by default.

6. Register a User. Navigate to "Registered Users" in the sidebar and create a new registered user. This represents the identity that will perform actions through your agent.

7. Save your Tool Pack. Review and save all your Tool Pack settings.

8. Connect to your agent or IDE. Copy the MCP entry URL from your Tool Pack settings.