Linear MCP

Linear's own MCP server gives your agent simple, secure access to your Linear workspace. Linear hosts and runs it, and its tools find, create and update issues, projects and comments, so you can plan and track work by asking in plain words. What you can do with it - Turn a planning document into a project, with issues, milestones and the links between them - Post standup notes as comments on the issues they're about - Investigate a bug from its issue, then write the findings back as a comment - Sum up what a team finished in its last cycle - Build a timeline of the work around a project, incident or topic - Draft an implementation plan, then create the parent issue and its sub-issues How it connects Linear hosts the server at https://mcp.linear.app/mcp. The first time your agent uses it, you sign in with your Linear account and approve access. You can also pass a Linear API key or OAuth token as a bearer token instead. Linear's docs walk through setup in Claude, Claude Code, Codex, Cursor, VS Code, Windsurf, Zed and more; agents without remote MCP support can reach it through mcp-remote. Read-only when you want it Connect to https://mcp.linear.app/mcp/readonly, which only ever exposes read tools, or grant only the read scope, and your agent can look things up but can't change anything. An API key with only the Read permission works the same way. Good to know Each sign-in covers one Linear workspace, so a second workspace needs its own connection. Teams on Okta can turn on enterprise-managed sign-in, so supported agents such as Claude authenticate through your Okta policies.