# Zendesk Support MCP Server & Agent Skill > Source: https://ibl.ai/developer/connectors/zendesk Connector · Customer service help desk Last updated: October 20, 2026 **ibl.ai publishes a free Zendesk Support agent skill: a SKILL.md that teaches an AI agent to read and write Zendesk Support data and expose it as an MCP tool. Download it, connect your own Zendesk Support credentials, and run the agent on ibl.ai Agentic OS, where you own all the code and the data.** Zendesk Support is a customer service ticketing system. An account stores tickets and their comments, end users and agents, organizations, groups, macros, views and help center content. ## What is the Zendesk Support API, and what can an agent read from it? JSON REST API for tickets, ticket comments, users, organizations, groups, views and search. Tickets: list, show, create, update and delete, plus create_many, update_many and destroy_many batch calls. - API: Zendesk Support API (Ticketing API) (REST) - Access: Issued by your administrator - Base URL: https://{subdomain}.zendesk.com/api/v2 - Authentication: OAuth 2.0 access token (Bearer); API token with email/token basic auth (deprecated) The caller must be a verified user. An admin registers an OAuth client in Admin Center; apps distributed to many Zendesk customers must use global OAuth tokens. Legacy API tokens live in Admin Center > Apps and integrations > APIs. Zendesk supports OAuth access tokens and asks customers on basic auth or API tokens to migrate to OAuth. API tokens can impersonate anyone in the account, including admins. ### What can an agent read from Zendesk Support? - **Tickets** — GET /api/v2/tickets (cursor or offset paging, max 100 per page) and GET /api/v2/tickets/{ticket_id}. - **Organization tickets** — GET /api/v2/organizations/{organization_id}/tickets. - **Recent tickets** — GET /api/v2/tickets/recent lists recently viewed tickets. - **Users and organizations** — Read end users, agents and organizations through the Support API. ### What can an agent write to Zendesk Support? - **Create tickets** — POST /api/v2/tickets or /api/v2/tickets/create_many. - **Update tickets** — PUT /api/v2/tickets/{ticket_id}; adding a public comment is visible to the requester. Confirm with the user first. - **Bulk update tickets** — PUT /api/v2/tickets/update_many. - **Delete tickets** — DELETE /api/v2/tickets/{ticket_id} or /api/v2/tickets/destroy_many. Confirm with the user first. Limits: Support API: 200 req/min (Team), 400 (Growth, Professional), 700 (Enterprise), 2,500 (Enterprise Plus). Update Ticket: 30 updates/10 min per user per ticket. Offset paging stops at 10,000 records; 429 includes Retry-After. Tickets hold customer personal data and free-text conversation history that may include account, payment or health details customers volunteer. Treat as personal data under applicable privacy law. ## How do I connect Zendesk Support to an AI agent over MCP? We could not confirm an MCP server in Zendesk, Inc.'s own documentation as of October 2026. The practical path is to host a small MCP server that wraps the Zendesk Support API (Ticketing API), or to give the agent the calls directly with the SKILL.md below. On ibl.ai an MCP connection is three records, and a working integration always needs all three: 1. **Register the server** — `POST …/mcp-servers/` with its URL, a transport (`sse`, `websocket` or `streamable_http`) and an `auth_type` of `none`, `token` or `oauth2`. 2. **Create a connection** that holds the credential, scoped to the whole organization (`platform`), to a single agent, or to each user (`user`). 3. **Enable it on the agent** — `mcp-tool` in `tool_slugs` and the server id in `mcp_servers`. Both lists are replaced, not merged, so read the settings first. For an API key or a service credential, one `token` connection at `platform` scope serves the whole organization; scope a connection to a single agent when that agent needs narrower access than the rest. The field reference is in [MCP server connections](https://ibl.ai/developer/platform/mcp/mcp-connections), and the [/iblai-api-agent-mcp](https://ibl.ai/developer/skills/iblai-api-agent-mcp) skill runs all three steps from a coding agent. ## What does the Zendesk Support agent skill do? The Zendesk Support skill is one SKILL.md file named `iblai-connect-zendesk`. It gives an agent the auth conventions, what to read, which writes need a person's confirmation, the ibl.ai MCP wiring, example prompts and guardrails. [Download the Zendesk Support SKILL.md](https://ibl.ai/developer/connectors/zendesk/SKILL.md) Save it as `.claude/skills/iblai-connect-zendesk/SKILL.md`, or in your agent's skills folder. The ibl.ai platform skills it calls come from one install: ``` npx skills add iblai/vibe --all ``` This connector skill is a starting point maintained on ibl.ai, not part of the iblai/vibe repository. It was checked against Zendesk, Inc.'s documentation on October 20, 2026. Test it against your own Zendesk Support setup before you rely on it. ### What can I ask a Zendesk Support agent to do? - “Show all urgent tickets that have been open more than 48 hours” - “Summarize the conversation on ticket #48213” - “Create a ticket for jane@example.com: refund request for order 1043” - “Which organizations opened the most tickets this week?” ## How do I run a Zendesk Support agent on ibl.ai? [Agentic OS](https://ibl.ai/product/agentic-os) is where the agent runs on ibl.ai: it holds the Zendesk Support MCP connection, the model the agent uses, its instructions and its conversation history. On ibl.ai you own all the code and the data, run it model-agnostic across any LLM, and pay with no per-seat pricing — so you can deploy anywhere, from your own cloud to a fully air-gapped network. - [AI agents for Enterprise](https://ibl.ai/solutions/enterprise) — what ibl.ai deploys in this sector ### Which ibl.ai agents work with Zendesk Support data? - [Customer Support](https://ibl.ai/solutions/enterprise/agent/customer-support-agent) — Enterprise ### Which ibl.ai platform skills does a Zendesk Support agent use? - [/iblai-api-agent-mcp](https://ibl.ai/developer/skills/iblai-api-agent-mcp) — MCP connectors for ibl.ai agents, end to end - [/iblai-vibe-agent-mcp](https://ibl.ai/developer/skills/iblai-vibe-agent-mcp) — Add the agent MCP tab (Model Context Protocol connector management with featured connectors, custom connectors, OAuth,… - [/iblai-api-agent-tool](https://ibl.ai/developer/skills/iblai-api-agent-tool) — Enable or disable an ibl.ai agent's tools via the platform API ## What else should I know before connecting Zendesk Support to an AI agent? ### Is there an official Zendesk Support MCP server? Not that we could confirm. We could not confirm an MCP server in Zendesk, Inc.'s own documentation as of October 2026. The SKILL.md on this page gives an agent the integration directly, and any MCP server you host can be registered on ibl.ai. ### Who can get Zendesk Support API credentials? The caller must be a verified user. An admin registers an OAuth client in Admin Center; apps distributed to many Zendesk customers must use global OAuth tokens. Legacy API tokens live in Admin Center > Apps and integrations > APIs. ### Does Zendesk Support data leave my infrastructure when an ibl.ai agent uses it? On ibl.ai, you own all the code and the data. Self-hosted in your cloud or data center, the agent, its MCP connections and its conversation logs stay inside your perimeter. Because the platform is model-agnostic, you can point the agent at a model you host, so Zendesk Support records need not reach a third-party model provider. ### Is the Zendesk Support agent skill free to use? Yes. The SKILL.md is a free download with no sign-up. It assumes you already have Zendesk Support credentials, and your agreement with Zendesk, Inc. still governs how you use its API. ## Which other data sources can an AI agent connect to alongside Zendesk Support? ### Which other Enterprise systems have a connector? - [Canvas LMS](https://ibl.ai/developer/connectors/canvas) — Learning management system - [Confluence](https://ibl.ai/developer/connectors/confluence) — Team wiki and knowledge base - [Databricks](https://ibl.ai/developer/connectors/databricks) — Data and AI platform (lakehouse) - [Docusign eSignature](https://ibl.ai/developer/connectors/docusign) — Electronic signature platform - [Esri ArcGIS](https://ibl.ai/developer/connectors/esri-arcgis) — Geographic information system (GIS) - [GitHub](https://ibl.ai/developer/connectors/github) — Source code hosting and collaboration - [Google Workspace](https://ibl.ai/developer/connectors/google-workspace) — Productivity and collaboration suite - [HubSpot](https://ibl.ai/developer/connectors/hubspot) — Customer relationship management (CRM) - [Jira](https://ibl.ai/developer/connectors/jira) — Work and issue tracking - [Microsoft 365 & SharePoint](https://ibl.ai/developer/connectors/microsoft-365) — Productivity and collaboration suite - [Okta](https://ibl.ai/developer/connectors/okta) — Identity and access management - [Oracle NetSuite](https://ibl.ai/developer/connectors/oracle-netsuite) — Cloud ERP and accounting - [PayPal](https://ibl.ai/developer/connectors/paypal) — Online payments platform - [Salesforce](https://ibl.ai/developer/connectors/salesforce) — Customer relationship management (CRM) - [SAP S/4HANA](https://ibl.ai/developer/connectors/sap-s4hana) — Enterprise resource planning (ERP) - [ServiceNow](https://ibl.ai/developer/connectors/servicenow) — IT service management and workflow platform - [Slack](https://ibl.ai/developer/connectors/slack) — Team messaging platform - [Snowflake](https://ibl.ai/developer/connectors/snowflake) — Cloud data warehouse - [Stripe](https://ibl.ai/developer/connectors/stripe) — Online payments and billing platform - [Workday HCM](https://ibl.ai/developer/connectors/workday-hcm) — Human capital management (HCM) Every connector, grouped by sector, is on the [connectors hub](https://ibl.ai/developer/connectors).