Linear

Agents can read Linear issues, create new ones, and update existing ones — useful for keeping engineering work in Linear while agents do the work in ThinkingMach.

Before you connect

• A Linear account with access to the workspace and teams you want agents to use.

That is all for browser sign-in. ThinkingMach registers its own OAuth client with Linear's MCP server when you connect, so there is no app to create in Linear's developer settings.

Connect Linear

1. Open Connectors and select Linear.
2. Read the access line above the main button. It says who the connection signs in as and which agents can use it. To pick a different identity or narrow the agents, select Change.
3. Select Continue to sign in, sign in as the account whose access the connection should have, and approve access.

ThinkingMach asks Linear for the read and write scopes, so agents can read issues and also create and update them. Which of those actions an agent may actually run is still your call on the Permissions tab.

Sign-in needs your ThinkingMach address to be HTTPS, or a local localhost address.

Use an API key instead

If browser sign-in is not suitable, select Change and choose Use an API key.

1. Create a personal API key in Linear's settings. Choose the permissions and teams the actions you plan to allow actually need.
2. Paste it into the Your Linear key field and select Connect.

A key restricted to Read permission works, and it is the simplest way to get a connection that genuinely cannot change anything in Linear. Workspace and role access still apply on top of the key.

Note: Linear's server exposes both read and write tools, whichever way you connect. A read-only key makes Linear refuse the writes; set them to Off on the Permissions tab too, so the action list matches what the key can actually do.

Note: Earlier versions of this guide had you register your own Linear OAuth application first. That is no longer needed. A connection you already made with your own application keeps working.

Choose access

Reach is whatever the authorizing Linear account has. That usually means every team and project that person can see, because Linear workspaces are commonly open internally.

Note: There is no team or project picker in ThinkingMach. Fields describing workspace, team, and project scope exist in the connector's definition, but they do not narrow what an agent can reach — the limit is the authorizing account's own access in Linear. If an agent should only touch one team's issues, authorize with an account restricted to that team, or rely on action settings and clear instructions rather than assuming a resource filter.

Issue creation and updates are writes. Leave them on Ask first while you are learning how an agent behaves — an agent that files issues enthusiastically is noisy for the whole team. Reads can stay Allowed. See Set action permissions.

Identity matters here for attribution: issues an agent creates or comments on appear under the authorizing account. A dedicated account makes agent activity distinguishable from a person's. See Use separate accounts for people and agents.

Try it

Find Linear issue ENG-142 and tell me its status, assignee, and latest comment. Do not change it.

Compare against the issue in Linear. A read of a known issue confirms the credential and the agent's permission without adding anything to your team's board.

Note: Illustrative task, not a recorded test result. Substitute an issue key from your own workspace.

Troubleshooting and limitations

Limitations: one workspace per connection. No team or project restriction inside ThinkingMach. Linear's own rate limits apply.

Related guides

• Jira, Asana, Todoist — other work tracking connectors.
• Use separate accounts for people and agents
• Set action permissions
• Linear API documentation