Skip to content

About

Linear issues and projects in your local WireCat store

Resources

Code of conduct

Contributing

Security policy

Stars

0 stars

Watchers

0 watching

Forks

Latest commit

 

History

10 Commits

Folders and files

NameName
Last commit message
Last commit date
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

linear: Linear CLI for AI agents

Linear issues and projects in your local WireCat store. One tool for you and for Claude Code, Codex or any agent that speaks MCP.

Docs · Install · Usage

  • Every operation of the Linear API is a command. linear api list shows them, each with its own flags, help and --json.
  • Your agent gets the same commands as tools. An MCP server and an agent skill come with it, no second codebase.
  • You decide what it may change. Each profile allows, asks or denies each command, and a delete needs a key of its own.

What you get

Ask your agent about Linear. It finds the right command with linear commands --json, runs it, and answers from the result. A command it may not run stops with a clear refusal before anything reaches Linear.

Why linear

  • The token stays in the system keyring, and every command names the profile it uses.
  • Every operation is tested against a strict fake built from the API description, in src/api.test.ts.
  • --dry-run shows what a write would send, and sends nothing.

Quick start

pnpm install
pnpm build
node dist/bin/linear.js doctor

Once it is on npm: npm install -g @wirecat/linear-cli, then linear doctor. Every command that uses an account starts with a profile, a name you choose: linear personal config show.

Sign in once with linear personal session start. It asks for the token and keeps it in the keyring.

Use it with your agent

linear personal mcp add claude-code
linear skill install

linear personal mcp check shows the tools your agent gets. mcp add refuses a profile whose tools may write until you review its permissions and pass --allow-writes. linear personal mcp config prints the setup for any other MCP client.

Over MCP nobody is there to answer ask, so the agent runs the API's writes and deletes without asking. Each one is kept as a run in linear personal runs list. To stop that, make the profile read-only with linear personal config set permissions.api readonly, or refuse one operation with linear personal config set permissions.api.<operation> deny. linear api list names the operations.

What it can do

docs/commands.md lists every command, and --help after any of them shows its flags.

Settings and permissions

linear personal config show prints the profile's settings. See docs/configuration.md.

Security

See docs/security.md, and SECURITY.md to report a problem.

When something goes wrong

Run linear doctor and see docs/troubleshooting.md. Report a bug on GitHub.

Development

Started from cli-template. Its design is in docs/dev/DESIGN.md, and the working rules are in AGENTS.md. Published as @wirecat/linear-cli.

About

Linear issues and projects in your local WireCat store

Resources

Code of conduct

Contributing

Security policy

Stars

0 stars

Watchers

0 watching

Forks

Releases

Packages

Used by

Contributors

Languages