Zendesk Platform MCP server
Zendesk Platform provides APIs for extending Zendesk with custom objects, data models, apps, and business logic. An MCP server for Zendesk Platform lets AI agents create custom data structures, manage apps, configure webhooks, and build complex automations on top of Zendesk.
Setting up an MCP server
This article covers the standard steps for creating an MCP server in AI Gateway and connecting it to an AI client. The steps are the same for every integration — application-specific details (API credentials, OAuth endpoints, and scopes) are covered in the individual application pages.
Before you begin
You'll need:
- Access to AI Gateway with permission to create MCP servers
- API credentials for the application you're connecting (see the relevant application page for what to collect)
Create an MCP server
Find the API in the catalog
- Sign in to AI Gateway and select MCP Servers from the left navigation.
- Select New MCP Server.
- Search for the application you want to connect, then select it from the catalog.
Configure the server
- Enter a Name for your server — something descriptive that identifies both the application and its purpose (for example, "Zendesk Support — Prod").
- Enter a Description so your team knows what the server is for.
- Set the Timeout value. 30 seconds works for most APIs; increase to 60 seconds for APIs that return large payloads.
- Toggle Production mode on if this server will be used in a live workflow.
- Select Next.
Configure authentication
Enter the authentication details for the application. This varies by service — see the Authentication section of the relevant application page for the specific credentials, OAuth URLs, and scopes to use.
Configure security
- Set any Rate limits appropriate for your use case and the API's own limits.
- Enable Logging if you want AI Gateway to record requests and responses for auditing.
- Select Next.
Deploy
Review the summary, then select Deploy. AI Gateway provisions the server and provides a server URL you'll use when configuring your AI client.
Connect to an AI client
Once your server is deployed, you'll need to add it to the AI client your team uses. Select your client for setup instructions:
Tips
- You can create multiple MCP servers for the same application — for example, a read-only server for reporting agents and a read-write server for automation workflows.
- If you're unsure which OAuth scopes to request, start with the minimum read-only set and add write scopes only when needed. Most application pages include scope recommendations.
- You can edit a server's name, description, timeout, and security settings after deployment without redeploying.
Authentication
Zendesk Platform uses OAuth 2.0 authentication. Create an OAuth application in your Zendesk Admin Center and obtain a Client ID and Client Secret. The OAuth endpoints are subdomain-specific: https://{subdomain}.zendesk.com/oauth/authorizations/new for authorization and https://{subdomain}.zendesk.com/oauth/tokens for token exchange. Key scopes include read and write (general access), apps:read and apps:write (manage apps), and custom_objects:read and custom_objects:write (manage custom objects). The Sunshine API is accessed via https://{subdomain}.zendesk.com/api/sunshine.
Available tools
The Zendesk Platform MCP server provides tools for managing custom objects, apps, webhooks, and advanced platform configurations.
Custom Objects
| Tool | Description |
|---|---|
| create_custom_object | Create a new custom object type |
| get_custom_object | Retrieve custom object schema |
| update_custom_object | Update custom object definition |
| delete_custom_object | Delete a custom object |
| list_custom_objects | List all custom objects |
| create_custom_object_record | Create a record of a custom object |
| update_custom_object_record | Update a custom object record |
| delete_custom_object_record | Delete a custom object record |
| list_custom_object_records | List records with filtering |
Apps Framework
| Tool | Description |
|---|---|
| create_app | Create a new Zendesk app |
| get_app | Retrieve app details |
| update_app | Update app configuration |
| delete_app | Delete an app |
| list_apps | List installed apps |
| create_installation | Install an app on the instance |
| list_installations | List app installations |
| update_installation | Configure app installation |
Webhooks & Targets
| Tool | Description |
|---|---|
| create_webhook | Create a webhook trigger |
| get_webhook | Retrieve webhook configuration |
| update_webhook | Update webhook settings |
| delete_webhook | Delete a webhook |
| list_webhooks | List configured webhooks |
| create_target | Create a webhook target endpoint |
| list_targets | List webhook targets |
Custom Fields & Admin Settings
| Tool | Description |
|---|---|
| create_custom_field | Create a custom field |
| get_custom_field | Retrieve field configuration |
| list_custom_fields | List custom fields |
| update_custom_field | Update field settings |
| list_roles | List available roles |
| list_groups | List user groups |
Tips
Plan relationships and field types carefully before creating custom objects in production — custom objects require careful schema design upfront.
Use custom_objects:read scope for read-only access to minimize security risk.
Test apps thoroughly in a development environment first — app installation is immediate and affects all users.
Include retry logic on the receiving endpoint to handle network failures in webhook configurations.
Always validate webhook signatures before processing events to ensure they originate from Zendesk.
Cequence AI Gateway