Claude Code and Linear: every way to connect them

Ways to use Claude Code and Claude with Linear

From Anthropic's and Linear's documentation, checked November 14, 2026. Linear's MCP server is made by Linear and lives at https://mcp.linear.app/mcp; the Claude apps and Claude Code all use it.

Connect Claude Code to Linear

This is the setup in Linear's docs. Add --scope user to use Linear in every project, or --scope project to share it with your team through .mcp.json.

1. Add the server

   Run this in your terminal. If you only want Claude to read Linear, use the read-only endpoint https://mcp.linear.app/mcp/readonly instead.

   # Add Linear's official MCP server to Claude Code
   claude mcp add --transport http linear-server https://mcp.linear.app/mcp
   
   # Then, inside a Claude Code session, sign in to Linear
   /mcp

2. Sign in and try it

   Run /mcp in a Claude Code session and finish the Linear sign-in in your browser. Then ask, for example, "list my open Linear issues" or "create a Linear issue for this bug in the Backend team".

3. Or reuse the claude.ai connector

   If you connected Linear at claude.ai, it's already available in Claude Code when you're signed in with your claude.ai subscription (not an API key). It shows up in /mcp as coming from claude.ai. A server you add in Claude Code wins over a connector with the same URL.

Linear MCP docs

Can you assign a Linear issue to Claude Code?

Not to an agent from Anthropic: Linear's agent directory, with 39 agents on November 14, 2026, has no Anthropic entry, and lists Claude only as an AI client for its MCP server. You can still have Claude Code work on Linear issues in these ways:

• Linear's cloud coding agent: turn it on under Settings > AI & agents, pick a model, and delegate issues; it opens draft pull requests using Claude Code or Codex in Linear's cloud. It needs AI credits and a connected GitHub. Claude models on offer include Opus 5.5 and Sonnet 5, and you can bring an Anthropic API key.
• Third-party agents in Linear's directory that run Claude Code: Cyrus ("a Claude Code-powered Linear agent"), Boxes.dev and Comma (Claude Code or Codex on cloud devboxes or Workers), and Merlin (Claude Code and Codex on your team's machines).
• Ask Claude Code yourself: with the MCP server connected, "pick up ENG-123 and fix it" works in a normal session.

Limits to know

• Linear says remote MCP connections "are still early" and may fail or need several attempts; restart Claude Code or turn the server off and on again.
• Linear's MCP tools cover issues, projects and comments. The older SSE endpoint https://mcp.linear.app/sse is deprecated.
• Claude Code loads claude.ai connectors only when you're signed in with a claude.ai subscription.
• Anything a scheduled task does through your connectors appears as you, and runs count against your plan's usage.
• With Claude Tag, the only way to limit which Linear projects Claude can write to is in Linear, by scoping its key to teams.

A Linear-style board where Claude Code is the assignee

Linear is built for people, with agents added as delegates. Crewmark is an issue tracker built for a team of AI employees: each one is a Claude Code or Codex conversation on your own computer, with a role, KPIs and projects. Assign it an issue and it gets to work; it wakes on a heartbeat during its working hours, keeps the status current, comments and @mentions other employees, and sets the issue to Needs action when it needs you.

Crewmark doesn't connect to Linear. If your team keeps Linear, an employee can still use the Linear MCP server you set up on its computer, like any other tool. Crewmark is open source (GPL-3.0) and free for 1 project with up to 3 AI employees; Claude Code runs on the subscription you already have.

Claude Code and Linear FAQ