Linear MCP in Claude Code

Quick answer: Install the Linear MCP server with npx -y @tacticlaunch/mcp-linear, add the JSON block below to ~/.claude/settings.json, restart Claude Code, and run /mcp to confirm the connection. Setup runs about 5 minutes on a fresh machine, verified on @tacticlaunch/mcp-linear as of April 15, 2026.

The Linear MCP server hands Claude Code a tool surface on top of the Linear API. After setup, the model can list teams, query issues, create tickets, update statuses, and read project state. For engineering teams that live in Linear, this removes the context switch of opening a new tab every time Claude needs to file or check a ticket.

This guide covers what you get after the wiring is done, the exact config, verification steps, prompt patterns that tend to work well, and the 4 issues that trip people up most often in the first week.

What you get when it is connected

Once the Linear server is attached, Claude Code can call the server tools from inside any conversation. You do not invoke the tools by hand. When you ask Claude a question the model decides which tool to call and parses the response for you. For teams that live inside Linear day to day, this replaces dozens of context switches per week with a single line in chat.

Tools exposed include list_teams, list_issues, create_issue, update_issue, list_projects, list_cycles, add_comment, get_user, search_issues. Everything is GraphQL under the hood, so the server batches related fields in a single round trip when possible. The free Linear plan caps at 250 issues, which you will not hit during normal use but matters for scripted bulk imports.

Prerequisites

A Linear account, a personal API key from linear.app/settings/api, and Node 20 or later. The API key inherits all the permissions of your Linear user.

If you use a version manager like nvm or asdf for Node, confirm the version Claude Code inherits. Open a terminal, run node -v, and note the output. Claude Code uses the Node it sees on PATH at launch, so a shell profile that sets the right version is the reliable path.

Install via npx

Run the package once with npx to verify it starts cleanly:

npx -y @tacticlaunch/mcp-linear

The first run downloads the package (a few MB) and starts the server on stdio. The server does not print much on success - it waits for MCP protocol messages on stdin. Press Ctrl-C to stop it. The actual runtime setup happens through Claude Code itself in the next step.

If the install fails with a network error, your npm registry may be blocked. Set npm config set registry https://registry.npmjs.org and retry. Behind a corporate proxy, also set HTTP_PROXY and HTTPS_PROXY in your shell.

Add the config block to ~/.claude/settings.json

Open ~/.claude/settings.json in your editor. If the file does not exist yet, create it with {} as the starting content. Add an mcpServers object with an entry for this server:

{
  "mcpServers": {
    "linear": {
      "command": "npx",
      "args": ["-y", "@tacticlaunch/mcp-linear"],
      "env": {
        "LINEAR_API_KEY": "lin_api_XXX"
      }
    }
  }
}

Save the file. If you already have other MCP servers defined, merge the new entry into the existing mcpServers object rather than replacing it.

Restart Claude Code fully (quit and reopen, not just close the window). The server is spawned lazily on the first tool call in a session, not at launch, but the config is read once per Claude Code start.

Verify the connection

Open a new Claude Code session and type /mcp at the prompt. You should see the server listed with a green or connected indicator. If it shows as failed, click into it for the stderr output - the error message usually points at the problem directly (bad token, wrong path, missing Node).

Run a trivial first prompt to confirm round trips work. Good smoke tests:

• For read servers: ask for a list of whatever resource type it exposes.
• For write servers: ask for a describe on a known resource first, then try a safe write on a test resource.

If the first prompt works, the wiring is done. From here on you interact with the server purely through normal prompts in Claude Code.

Example prompts that work well

Here are prompts that tend to get good responses once the server is attached:

• Create a Linear issue in the team Engineering titled Investigate slow dashboard queries with priority high and assign to me.
• List all issues assigned to me that are in progress, sorted by updated date.
• Show me every issue in the current cycle for team Backend that is still not started.
• Update issue ENG-432 to status In Review and add a comment saying PR is ready at github.com/foo/bar/pull/100.
• Search Linear for any issue whose title contains the word regression filed in the last two weeks.
• Read issue ENG-500 and tell me the description, status, assignee, and linked pull request.

Claude will chain tool calls on its own when the prompt implies several steps. For a summarize-then-write flow the model will often call read tools first, then a single write tool at the end. If a prompt keeps burning tool calls, narrow it: specify the resource ID, the time range, or the exact field you want rather than asking Claude to scan everything.

Environment variable security

The API key lives in LINEAR_API_KEY. It is tied to your Linear user, so anything the key can do, Claude can do. If you need stricter scope, create a Linear OAuth app instead and use that token, which supports fine-grained scopes. Rotate the key from linear.app/settings/api if it leaks.

A general rule across every MCP server: never paste secrets directly into settings.json that lives in a shared or git-tracked directory. Keep the actual secret values in your shell profile (~/.zshrc, ~/.bashrc, or a 1Password-cli helper), export them at shell start, and reference the variable names from the Claude config. That way the secret stays on your machine and the config file is safe to share with teammates.

On macOS, terminals launched from Spotlight or from the Dock both inherit the shell profile. If you launch Claude Code from a GUI shortcut that does not go through a shell, env vars may not propagate - launch from a terminal instead.

Troubleshooting

Tool calls return AUTHENTICATION_ERROR. The API key is wrong or has been revoked. Regenerate at linear.app/settings/api, update the env var, and restart Claude Code.

Cannot see issues from another team. The API key only sees teams your Linear user is a member of. Ask a workspace admin to add you to the team, or use a workspace-scoped OAuth token.

Status updates fail with state not found. Workflow states differ per team. Ask Claude to list the states for the issue team first, then map your intent (In Review, Done) to the exact state name used by that team.

Slow responses on large queries. The Linear GraphQL API paginates at 50 items. For large scans, ask Claude to use cursor-based pagination rather than one giant query.

For any issue not listed here, the first step is /mcp inside Claude Code to see the current status and any recent stderr from the server. The second step is running the exact npx command from your terminal to see if the server starts cleanly outside Claude Code. Between those two checks, most problems become obvious within a minute.

Next steps

Once the Linear server is attached and verified, the useful next move is writing a short prompt template you keep in your notes. List the 3 or 4 prompts you run most often against this server, and paste them into Claude Code when needed. Over a few weeks you build a personal command library that gets real work done without typing much.

For team projects, commit a .mcp.json at the repo root with the same structure. Everyone on the team gets the server wired up automatically on first open, and individual secrets stay in shell profiles. That is the setup pattern that scales past a single developer.