Connect Zendesk with Unblocked to ground answers in real customer tickets

Zendesk tickets capture how customers actually experience bugs and edge cases, often with detail that never makes it into an engineering ticket. Unblocked makes the tickets from your selected brands available as cited evidence, so an agent can connect a reported issue to the code that caused it.

Zendesk context is reconciled with your code, pull requests, and docs, so an agent can trace a customer-reported problem back to the change that introduced it, or confirm whether a fix already shipped.

Once connected, any MCP-compatible coding agent — Claude Code, Cursor, Windsurf, GitHub Copilot, Codex — can pull this context through a single Unblocked MCP server connection.

What you get

• Tickets as context — Unblocked indexes support tickets from the Zendesk brands you select and cites the original ticket in its answers.
• Brand-level scoping — Choose which Zendesk brands Unblocked can access, and update the selection anytime from Settings → Data Sources → Zendesk.
• Kept current automatically — Unblocked checks Zendesk for new and updated tickets about every 15 minutes.
• Cross-source synthesis — Zendesk tickets are combined with your code, pull requests, docs, and Slack threads into a single knowledge graph.

Need screenshots or troubleshooting?This is a concise connection summary. Follow the complete setup guide ↗

Prerequisites

• An Unblocked account (free to start).
• A Zendesk account and its subdomain (e.g. acme for acme.zendesk.com), with permission to authorize third-party applications.
• An MCP-compatible coding agent (Claude Code, Cursor, Windsurf, etc.) to use the context in your editor.

Step 1: Connect Zendesk to Unblocked

1. In Unblocked, go to Settings → Data Sources → Connect another data source, and under Project management select Zendesk.
2. Enter your Zendesk subdomain (e.g. acme for acme.zendesk.com) and click Connect.
3. Sign in to Zendesk and click Allow to authorize Unblocked.
4. Select the Zendesk brands to index, then click Save Settings.

Step 2: Install the Unblocked MCP server

On macOS or Linux, one command auto-detects and configures your supported agents (Claude Code, Cursor, Windsurf, GitHub Copilot, Codex, OpenCode, VS Code):

On Windows, or when you prefer remote MCP, add the server manually using the configuration below, or follow the manual install guide ↗.

claude mcp add -s user --transport http unblocked https://getunblocked.com/api/mcpsse

{
  "mcpServers": {
    "unblocked": {
      "url": "https://getunblocked.com/api/mcpsse"
    }
  }
}

https://getunblocked.com/api/mcpsse

To give Claude Code, Cursor, GitHub Copilot, Codex, or another MCP-compatible AI coding agent access to Zendesk context, connect Zendesk to Unblocked and add the single Unblocked MCP server to your agent.

Unblocked acts as the MCP context layer for your Zendesk data, searching tickets, brands alongside your other connected sources and returning cited results through these tools:

• context_researchMulti-source research across your Zendesk tickets, plus your code, pull requests, and other connected sources. Returns a synthesized answer with citations back to the ticket it used.
• context_get_urlsFetches the full content behind a Zendesk ticket URL your agent encounters — plus GitHub, Jira, Linear, Confluence, Slack, and more.
• research_taskInvestigates a broader question across your Zendesk tickets, code, pull requests, docs, and Slack together, synthesizing a research brief instead of a single citation — useful when you don’t know which ticket to start from.

Questions you (or your agent) can ask Unblocked about your Zendesk data:

• Which Zendesk tickets mention timeouts in the checkout flow?
• What did the customer report before we shipped the fix for this bug?
• Are there any open tickets related to the recent API change?
• What was the resolution on the ticket about failed webhook deliveries?