Linear Zendesk Integration: Connect Them for Your AI Agent (2026)
A bug report lands in Zendesk, and it needs to travel: the customer wants it fixed, and your engineers live in Linear. Getting the two to talk — so a ticket becomes an issue, and an issue's status makes its way back to the customer — is one of the most common asks on any support-plus-engineering team. There's more than one way to do it, depending on what you actually need.
This guide covers both: the native Linear–Zendesk app (and where it stops), and how to give your AI agent live Linear issue lookups and creation right inside a ticket using a Custom Tool.
Framing first. Macha runs on top of the Zendesk you already use — it's an AI-agent layer, not a Zendesk or Linear replacement. Your agents keep working in Zendesk; Macha reads the ticket, reasons, and reaches into Linear to file, link, or check status.
The native option — and where it stops
Linear does offer a native Zendesk integration. You install it from the Zendesk Marketplace, it drops a Linear widget into the ticket sidebar, and from there an agent can create a Linear issue from the ticket, link an existing one, and get status updates back when the bug is fixed. If a human agent manually triaging and filing issues is all you need, and you're on a Linear plan that includes it, that may be enough.
Where it stops:
- It's agent-operated, not agent-decided. The widget lets a person create or link an issue. It doesn't let an AI agent decide mid-conversation that a message is a bug worth filing, write the title and description, and do it.
- It's plan-gated. The native integration has historically sat on Linear's Business and Enterprise tiers.
- It's fixed. You get the fields and flow the app exposes — not the specific issue payload, team routing, or status query your workflow needs.
For a lot of teams, the sidebar widget is fine. For anyone who wants their AI agent to actually use Linear, there's a lighter, more flexible path.
What you actually want: the agent using Linear live
The high-value version of this integration isn't a sidebar button — it's the agent doing the work. A customer reports a crash in Zendesk; the agent recognizes it's a genuine bug, files a Linear issue with a clean title and repro steps pulled from the conversation, and later reads the issue's status back to answer "yes, engineering has this fixed in the next release." That's what a Custom Tool enables.
How to connect them with a Custom Tool
A Custom Tool is a single action you define once and point at Linear's API. No plan gate, no code.
1. Point it at the Linear API. Linear exposes a GraphQL API (with an API key or OAuth); you give Macha the endpoint and credentials. The built-in Sidekick can scaffold the request from a plain-English description if you'd rather not fill in the form.
2. Define the action. Give it a label and a description the AI uses to decide when to call it — e.g. "Create a Linear issue from a bug report" or "Get the status of a Linear issue by ID" — set the method and URL (a GraphQL mutation or query against the Linear API, with placeholders for the fields the agent will fill), and choose Read or Write. Checking status is a Read; creating an issue is a Write, which requires confirmation before it runs.
3. The agent uses it live. Once the tool exists, the agent calls it mid-ticket — filing the issue from a bug report, or reading a linked issue's state — and reasons over what comes back to answer the customer or take the next step.
Read vs Write, and staying safe
Because a Custom Tool can reach into Linear, the guardrails matter: Read tools (status lookups) are free to call; Write tools (create an issue, add a comment, change a label) require confirmation. Each tool is scoped to one action, permissioned per agent, and every call is audited. Linear's API key or OAuth handles credentials, so secrets never live in the conversation.
Teams usually build a few Linear tools and group them — a "create issue," a "get issue status," a "link to existing" — alongside tools for their other systems.
Native app vs Custom Tool — which to use
- Use the native Linear app if you want a human agent to manually create or link issues from the ticket sidebar and you're on a Linear plan that includes it.
- Use a Custom Tool when you want your AI agent to file or look up Linear issues from the ticket on its own, you need a specific issue payload or query the app doesn't expose, or you'd rather not be plan-gated. The two can coexist.
Beyond the lookup
Once the agent can reach Linear, the same pattern covers more: file a bug with repro steps, read an issue's status to update the customer, add a comment linking the ticket, route to the right team, or check whether a fix has shipped. And because Custom Tools aren't Linear-specific, the same approach connects your CRM, billing system, or internal API — see the Custom Tools integration directory for 200+ tools, or the full pillar on building custom Zendesk integrations.
The bottom line
Linear's native app puts a create-issue button in the sidebar for a human to click. A Custom Tool puts Linear in your AI agent's hands — filing issues and reading status live, decided in context, on any plan, no code. You describe the action, point it at the Linear API, and your Zendesk agents can use it inside a ticket with Read/Write guardrails and a full audit trail.
Ready to try it? See how Custom Tools work, browse the integration directory, or start a free trial and wire up your first Linear tool today.
Frequently asked questions
Does Zendesk have a native Linear integration? Yes — Linear's native Zendesk app installs from the Marketplace, adds a widget to the ticket sidebar, and lets a human agent create or link issues (historically on Linear's Business and Enterprise plans). A Custom Tool adds live, AI-agent-driven issue creation and lookups on any plan.
Do I need an engineer to connect Linear to Zendesk this way? No. You describe the action in plain English and Macha's Sidekick scaffolds the Linear request, auth, and parameters. Technical teams can go deeper with full control over the GraphQL query or mutation, headers, and response mapping.
Can the agent create issues in Linear, or only read them? Both. Reads (status lookups) run freely; writes — creating an issue, adding a comment — require a confirmation step, and you control which agents can use them.
Is it secure? Yes. The tool is scoped to a single action, permissioned per agent, authenticated via Linear's API key or OAuth, and every call is audited.
Add AI agents to your Zendesk
Macha resolves tickets end to end, right on top of Zendesk — no migration.
Shopify
Stripe
Slack
Notion
Google Workspace
Confluence

