Zendesk Talk MCP server

Zendesk Talk is a cloud-based voice and call center solution integrated with Zendesk Support. An MCP server for Zendesk Talk lets AI agents manage inbound and outbound calls, track phone numbers, configure IVR menus, and access call recordings and analytics.

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

1. Sign in to AI Gateway and select MCP Servers from the left navigation.
2. Select New MCP Server.
3. Search for the application you want to connect, then select it from the catalog.

Configure the server

1. Enter a Name for your server — something descriptive that identifies both the application and its purpose (for example, "Zendesk Support — Prod").
2. Enter a Description so your team knows what the server is for.
3. Set the Timeout value. 30 seconds works for most APIs; increase to 60 seconds for APIs that return large payloads.
4. Toggle Production mode on if this server will be used in a live workflow.
5. 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

1. Set any Rate limits appropriate for your use case and the API's own limits.
2. Enable Logging if you want AI Gateway to record requests and responses for auditing.
3. 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:

• Claude Desktop
• Claude Code
• Cursor
• VS Code
• Windsurf

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 Talk 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 for Talk are talk:read (view call history and recordings) and talk:write (manage calls and settings). The Talk API base URL is https://{subdomain}.zendesk.com/api/v2/channels/voice.

Available tools

The Zendesk Talk MCP server provides tools for managing calls, phone numbers, agents, and call analytics.

Call Management

Tool	Description
create_call	Initiate an outbound call
get_call	Retrieve call details by ID
list_calls	List calls with filtering and date range
update_call	Update call properties (forward, hold, transfer)

Phone Numbers

Tool	Description
list_phone_numbers	List phone numbers and their settings
get_phone_number	Retrieve phone number details
update_phone_number	Update routing and configuration
create_phone_number	Purchase or add a new phone number

Agent Availability

Tool	Description
get_agent_status	Check agent availability status
set_agent_status	Update agent status (available, unavailable, break)
list_agents	List agents and their status

Call Recordings

Tool	Description
list_recordings	List call recordings with filtering
get_recording	Retrieve recording metadata and download URL
delete_recording	Delete a recording

Analytics & Statistics

Tool	Description
get_call_statistics	Retrieve call metrics (volume, duration, etc.)
list_call_statistics	List statistics over time period

Tips

Verify that the agent is available using get_agent_status before making outbound calls to avoid failed calls.

Download important calls promptly for archival — recordings are stored for a limited retention period.

Check both agent availability and phone number configuration when routing calls to agents to ensure successful routing.

Use call statistics to identify peak calling times and adjust staffing accordingly.

Implement retry logic for failed outbound calls rather than failing immediately.