You can connect Linear to Claude in a few minutes using the Model Context Protocol (MCP), and once it’s connected, Claude can look up issues, check cycles, and create or update tickets without you switching tabs. This guide covers both ways to do it: Linear’s official remote MCP server connected directly, and connecting it through a gateway if you also use other AI clients or tools.

What the Linear MCP server actually does

Linear publishes an official remote MCP server at mcp.linear.app/mcp. It exposes your workspace’s issues, projects, and cycles as tools Claude can call directly, instead of you copying ticket details into the chat by hand. In practice that means prompts like:

  • “What’s still open in the current cycle for the mobile team?”
  • “Create an issue for the login bug we just discussed, assign it to me.”
  • “Summarize everything tagged ‘P1’ that’s still unresolved.”
  • “Update the status of ENG-482 to In Review.”

Claude reads and writes through the same permissions your Linear account already has — it isn’t a separate export or integration, it’s your account acting on your behalf.

Option 1: Connect Linear to Claude directly

Claude supports remote MCP servers natively. The short version of the setup:

  • Open Claude’s connector or MCP settings.
  • Add a remote server pointing at Linear’s MCP endpoint.
  • Sign in with your Linear account when prompted — this is standard OAuth, so Claude never sees your Linear password, and you can revoke access from Linear’s own settings at any time.

That’s enough for one person using Linear inside Claude. The tradeoffs show up once you add a second tool or a second person: every additional AI client (ChatGPT, Cursor, an agent) needs its own copy of that same connection, its own OAuth grant, and its own place where the config can go stale or get lost.

Option 2: Connect it once, through a gateway

If you’re already juggling more than one MCP server, or more than one AI client, wiring each pair directly gets old fast — that’s the connection sprawl we wrote about in what an MCP gateway is. The alternative is connecting Linear (and everything else) to one gateway URL, then pointing every AI client at that single URL instead of reconfiguring each one.

With gate specifically, connecting Linear looks like this: add gate’s gateway URL to Claude once, then pick Linear from the Linear server page in the directory and sign in with OAuth the same way you would directly. From then on, Linear’s tools are available in every client connected to your gate URL — Claude, ChatGPT, or Cursor — without a second setup step. You can see the full list of servers set up this way on the MCP servers page.

Why the connection method matters for an issue tracker

Linear is the kind of server worth a moment’s thought before you connect it: an AI client with write access can create, edit, and reassign issues at whatever pace it is prompted to, across every project your account can touch. A few things worth checking before or right after you connect:

  • Is it the official endpoint? Connect Linear’s documented server (mcp.linear.app), not a third-party mirror claiming to proxy it.
  • What can it write, not just read? A tracker server like Linear’s can create and edit issues, not just read them. Know that before you hand it a broad prompt like “clean up the backlog.”
  • Who else on your team can reach it? If more than one teammate connects Linear to their own AI client, you likely want a shared, revocable setup rather than everyone holding their own token. That’s the same access-control question we cover in MCP access control for teams.

You can run a quick, no-signup check on any server’s tool list — including ones that require OAuth, once connected — with gate’s free MCP security scanner, which looks for prompt injection and hidden instructions in tool descriptions before you rely on a server day to day.

Troubleshooting the connection

A few things that commonly go wrong when connecting any remote MCP server, Linear included:

  • OAuth loop or sign-in fails. Make sure you’re signed into the right Linear workspace in your browser before authorizing — a mismatched workspace is the most common cause.
  • Claude can’t find an issue you know exists. Linear’s tools respect your permissions in Linear itself — if an issue lives in a team or project you don’t have access to, Claude won’t see it either.
  • Tools disappear after a Linear update. Remote servers can change their tool list without warning. If you’re connected through a gateway, that kind of change is exactly what drift detection is meant to catch.

The bottom line

Connecting Linear to Claude with MCP takes a few minutes either way: point Claude directly at Linear’s server and sign in, or connect it once through a gateway if you want the same Linear access available in every AI client you use, with the server’s tools checked before they go live. Either way, treat the OAuth grant for an issue tracker like Linear the same way you’d treat any other tool with write access — worth a minute’s thought before you say yes.