start here

start using Linear with your agents

sign up, open a project, and authorise Linear from its connectors settings.

Start 7-day trial with Linear
integrationsconnectorupdated
schematic diagram of the work aldena agents do through Linear
Linear

ai agent for linear: start the work when an issue lands

connect linear to a project and its agents wake on created, updated and commented issues in the teams they watch, then build the change in their conversation's sandbox.

events
3
resource types
1
access grants
1

linear is where the work is described, and an aldena project is where it gets done. connecting linear to a project turns new issues, updates and comments into runs: an agent subscribes to an issue or a whole team from a chat, and the next matching event starts a run in that chat, or in a new chat in the same project when the routine opens one per event. because each conversation in the project gets its own sandbox, the agent can then build what the issue describes. creating, updating and commenting on issues goes through linear's own mcp server.

subscribing from a chat

linear_subscribe takes a resource, the events to watch, and what the agent should do when one arrives. the resource is an issue identifier such as ENG-42, or a team key such as ENG for every issue in the team. an issue routine fires when the issue is updated, including a workflow state change, or commented on, and a team routine also fires when a new issue is created. linear_unsubscribe takes an event routine off again, and the project's Settings → Routines lists every routine the agents hold.

each notification carries the event routine, the actor, a one-line summary and a link. a new issue also carries its description, and a comment carries the comment body. the text is fenced off as untrusted data and capped at 4,000 characters, so an issue can inform the agent but cannot instruct it.

going beyond triggers with linear's mcp server

for searching, creating, updating, commenting on and relating issues, add linear's mcp server to the same project. it acts as the person who signs in to it.

  1. open the project's Settings → Connectors, and under MCP servers press Marketplace.
  2. install Linear. it installs as linear-mcp, so it does not clash with the connector.
  3. open the sign-in link it gives you and approve access in the browser.

once it is connected, agents reach its tools through mcp_search and mcp_call, each tool gets its own row in the project's permissions, and every action runs as the person who signed in, not as aldena. the mcp servers page covers the rest.

example tasks

  • 01

    watch the platform team and draft a plan whenever something new arrives.

    the team routine starts a run in this chat for each new issue, with the description in the notification. the agent reads the repository in the conversation's sandbox and proposes an approach here.

    linear_subscribegithub_git_syncbash
  • 02

    take ENG-310, build it, and move it to in review when the branch is up.

    the agent does the work in the conversation's sandbox, pushes a branch, then moves the issue to in review and comments the branch through linear's mcp server.

    github_git_syncbashgithub_git_pushmcp_searchmcp_call
  • 03

    stop watching ENG-42.

    the agent lists its routines, finds the event routine on ENG-42, and removes it, so updates there no longer start runs.

    list_routineslinear_unsubscribe

what it will not do

the connector does not search, create, update, comment on or delete issues, and cycle, linear project and member administration are out of reach. an agent cannot subscribe to a team the connected account cannot see, and no event starts a run while the connection waits for a reconnect.

what starts a run

every Linear event an agent can subscribe to, grouped by resource. an agent subscribes from a chat with linear_subscribe, and each matching event starts a run in that chat, or in a new chat in the same project when the routine opens one per event.

issue3 events
  • issue.created
  • issue.updated
  • issue.commented

what you grant

aldena asks Linear for exactly this access on the consent screen, the same set for every project. there is nothing to pick, and nothing else is requested.

  • Read the workspace
    read

    Check the teams and issues agents subscribe to.

how to connect Linear

connecting Linear takes one authorisation round trip, started from inside the project that needs it.

  1. open the project's connectors settings

    connections belong to a project, not to your account or the team. open the project that needs Linear, go to settings → connectors, and press connect. other projects stay untouched.

  2. authorise with a real account

    any member of the project can start the connection, and they authorise as themselves. Linear asks only for the fixed access listed above, with no scopes to choose.

  3. an agent subscribes from a chat

    ask an agent in a project chat to watch something in Linear. it calls linear_subscribe with the resource, events and intent, and settings → routines lists each routine it holds.

  4. a matching event starts a run

    each matching event starts a run with the event and its content in hand, in the chat where the agent subscribed or in a new chat in the same project when the routine opens one per event. disconnecting Linear stops every subscription to it.

data handling and security

a connector holds one credential and turns Linear events into runs. the credential stays inside the project that connected it, and event text is data, never instructions.

  • one connection, one project

    the Linear credential is stored against the project it was authorised in. no agent in another project can use it, and there is no team-wide connection to inherit by accident.

  • tokens encrypted at rest

    the Linear token is encrypted before it is stored, and it never appears in a chat or in an agent's prompt. agents get the events, not the credential.

  • events only where a routine watches

    aldena verifies each delivery came from Linear. an event starts a run only for a routine it matches, in the chat that set the routine up or in a new chat in the same project when the routine opens one per event. nothing starts while the connection needs a reconnect.

  • event content is untrusted

    event text may come from a stranger. it reaches the agent as fenced data capped at 4,000 characters, and the agent is told never to follow instructions in it.

  • revocation is one click

    disconnect Linear and the project's event routines on it stop at once, along with the stored credential.

the permissions tab in project settings with reads on allow, edits on ask, and write file and bash on deny

each Linear tool agents hold has its own allow, ask or deny row in the project's permissions. see human in the loop for approvals and isolated projects for isolation.

faq

can an ai agent create and update linear issues?

yes, through linear's own mcp server rather than the connector. install linear from the project's mcp marketplace with a browser sign-in, and agents create, update, comment on and move issues through mcp_call, acting as the person who signed in. the connector itself only starts runs from linear events.

what does the linear connector do, then?

it starts runs. an agent subscribes to one issue or a whole team with linear_subscribe, and each created, updated or commented issue starts a run with the event in hand, in that chat or in a new chat in the same project when the routine opens one per event. that is how triage can begin the moment something lands in a team's inbox, without anyone forwarding it.

which linear access does aldena ask for?

the read scope and nothing else. aldena uses it to check that the team or issue an agent subscribes to exists, and linear delivers the events through a webhook. there is nothing to pick on the consent screen, and the connector cannot change anything in the workspace.

what does a linear event notification contain?

the event routine, the actor, a one-line summary and a link. a new issue also carries its description, and a comment carries the comment body. that text is fenced off as untrusted data and capped at 4,000 characters, and an update arrives with the summary alone.

can the agent do the engineering work, not just the ticket admin?

yes, and that is the reason to connect linear to a project rather than to a chat bot. each conversation in the project gets its own sandbox, so the agent a linear event woke up clones the repository, writes the change, runs the tests and pushes a branch before it updates the issue through linear's mcp server.

ready when you are

spin up your first project.

one project per client, product, or piece of work, staffed with intake, requirements, build and code review agents.