
List Help Center articles with pagination. Optionally filter by section ID or label names. To fetch the next page, pass pageinfo.cursor as the page parameter. Check pageinfo.hasnextpage to see if more results exist.
Get a specific Help Center article by ID. Use list_articles to find valid article IDs.
Create a new Help Center article within a section. Articles contain the actual help content with title and body.
Update an existing Help Center article. Use get_article to retrieve the current values first.
Delete a Help Center article. This permanently removes the article from the knowledge base.
List Help Center categories with pagination. To fetch the next page, pass pageinfo.cursor as the page parameter. Check pageinfo.hasnextpage to see if more results exist.
Get a specific Help Center category by ID. Use list_categories to find valid category IDs.
Create a new Help Center category. Categories organize sections and articles.
Update an existing Help Center category. Use get_category to retrieve the current values first.
Delete a Help Center category. WARNING: This will also delete all sections and articles within the category.
Get a specific organization by ID
List organizations with optional filtering
Create a new organization
Update an existing organization
Delete an organization
Search organizations using query
Get users in an organization
Get tickets for an organization
List organization memberships
Create an organization membership
Delete an organization membership
Create multiple organizations at once
Update multiple organizations at once
Merge two organizations
List Help Center sections with pagination. Optionally filter by category ID. To fetch the next page, pass pageinfo.cursor as the page parameter. Check pageinfo.hasnextpage to see if more results exist.
Get a specific Help Center section by ID. Use list_sections to find valid section IDs.
Create a new Help Center section within a category. Sections organize articles within categories.
Update an existing Help Center section. Use get_section to retrieve the current values first.
Delete a Help Center section. WARNING: This will also delete all articles within the section.
Get a specific ticket by ID
List tickets with optional filtering
Create a new ticket
Update an existing ticket
Delete a ticket
Search tickets using query
Get comments for a ticket
Add a comment to a ticket
Add an INTERNAL (staff-only) note to a ticket — always private, no public option in this tool. Use when a comment must stay internal. Note: this is a property of THIS tool only; addticketcomment, updateticket, createticket, and bulkupdatetickets can each still post public replies, so for an internal-only setup grant only this tool and withhold those four.
Get audit history for a ticket
Update multiple tickets at once
Get a specific user by ID
List users with optional filtering
Create a new user
Update an existing user
Search users using query
Suspend a user
Unsuspend a user
Delete a user
Get identities for a user
Create a new identity for a user
Update a user identity
Delete a user identity
Make a user identity primary
Create multiple users at once
Update multiple users at once
Get the status of a bulk operation job
Validate Zendesk credentials. Verifies credentials during setup.

In an mcp.json file, add the configuration below, and restart Cursor.
Learn more in the official documentation ↗
1{
2 "mcpServers": {
3 "agent-handler": {
4 "url": "https://ah-api-develop.merge.dev/api/v1/tool-packs/{TOOL_PACK_ID}/registered-users/{REGISTERED_USER_ID}/mcp",
5 "headers": {
6 "Authorization": "Bearer yMt*****"
7 }
8 }
9 }
10}
11Open your Claude Desktop configuration file and add the server configuration below. You'll also need to restart the application for the changes to take effect.
Make sure Claude is using the Node v20+.
Learn more in the official documentation ↗
1{
2 "mcpServers": {
3 "agent-handler": {
4 "command": "npx",
5 "args": [
6 "-y",
7 "mcp-remote@latest",
8 "https://ah-api-develop.merge.dev/api/v1/tool-packs/{TOOL_PACK_ID}/registered-users/{REGISTERED_USER_ID}/mcp",
9 "--header",
10 "Authorization: Bearer ${AUTH_TOKEN}"
11 ],
12 "env": {
13 "AUTH_TOKEN": "yMt*****"
14 }
15 }
16 }
17}Open your Windsurf MCP configuration file and add the server configuration below.
Click on the refresh button in the top right of the Manage MCP server page or in the top right of the chat box in the box icon.
Learn more in the official documentation ↗
1{
2 "mcpServers": {
3 "agent-handler": {
4 "command": "npx",
5 "args": [
6 "-y",
7 "mcp-remote@latest",
8 "https://ah-api.merge.dev/api/v1/tool-packs/<tool-pack-id>/registered-users/<registered-user-id>/mcp",
9 "--header",
10 "Authorization: Bearer ${AUTH_TOKEN}"
11 ],
12 "env": {
13 "AUTH_TOKEN": "<ah-production-access-key>"
14 }
15 }
16 }
17 }In Command Palette (Cmd+Shift+P on macOS, Ctrl+Shift+P on Windows), run "MCP: Open User Configuration".
You can then add the configuration below and press "start" right under servers. Enter the auth token when prompted.
Learn more in the official documentation ↗
1{
2 "inputs": [
3 {
4 "type": "promptString",
5 "id": "agent-handler-auth",
6 "description": "Agent Handler AUTH_TOKEN", // "yMt*****" when prompt
7 "password": true
8 }
9 ],
10 "servers": {
11 "agent-handler": {
12 "type": "stdio",
13 "command": "npx",
14 "args": [
15 "-y",
16 "mcp-remote@latest",
17 "https://ah-api-develop.merge.dev/api/v1/tool-packs/{TOOL_PACK_ID}/registered-users/{REGISTERED_USER_ID}/mcp",
18 "--header",
19 "Authorization: Bearer ${input:agent-handler-auth}"
20 ]
21 }
22 }
23}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.
Here are just a few ways to use it:
Here are some popular tools across data types:
Organizations
Tickets
Users
Merge Agent Handler’s Zendesk MCP server comes with platform-level capabilities:
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:
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.
Yes, Agent Handler for Employees lets your employees connect Claude, ChatGPT, Microsoft Copilot, Cursor, and other MCP-compatible AI tools to Zendesk without bypassing IT governance.
Instead of setting up direct connections with personal credentials that IT can't monitor or revoke, each employee authenticates through Agent Handler and gets individual credentials tied to their identity.
IT also provisions access by role or group via SCIM. A support agent, for example, gets Zendesk access to resolve tickets, Jira to track related bugs, and Slack to coordinate with engineering; while an account manager gets Zendesk access to review customer history, Salesforce to track account health, and Gmail to manage follow-up communications.
Every tool call an employee's AI makes to Zendesk is also inspected against your DLP rules and logged to a searchable audit trail, giving security teams full visibility into what data was accessed and by whom.
Whether you're an engineer experimenting with agents or a product manager looking to add tools, you can get started for free now