Claude Linear connectorWhat Claude can do in your Linear account.
The Claude Linear connector exposes 22 tools. 6 of them read your issues, projects and comments, 5 create or update them, and 11 are documented nowhere. Below: what Claude reads, what it writes, what it asks first, and what Linear says that Anthropic does not.
Verified Trustpilot reviews · AI, automation & growth agency
What changes once Claude can work in Linear
The gap between a conversation and your tracker shrinks. Standup notes, a planning document or a bug report you are discussing with Claude can become issues, comments and projects in Linear without copy and paste, and questions about what the team is working on get answered from the tracker itself.
Turn a plan into tracked work. From a planning document, Claude can call create_project and then create_issue for each piece of work, so the structure lands in Linear instead of staying in a chat.
Keep issues current after a meeting. list_my_issues and get_issue find what was discussed, update_issue changes it, and create_comment records the progress or the blocker on the right issue.
Get a status without opening five views. list_issues, list_projects and get_project give Claude the material to summarize where a project stands.
What the connector does not do: act by itself. No tool fires when an issue changes state or a cycle ends; Claude only calls them while it answers you. Half of the list also has no official description: cycles, documents, statuses, labels, teams and users appear by name only, so this page does not say what those tools do. If you need issues created automatically from another app on every event, that belongs to automation, covered on our Linear n8n integration and Linear Make integration pages. A different job, not a competing one.
Five words to know before you connect
The vocabulary around this connector, in one minute.
- Connector
- The link you set up once between Claude and an account you already own, so Claude can work in it while it answers you.
- Tool
- One named action a connector gives Claude. Claude picks the tools it needs by itself, and the directory lists them by name.
- Authorization
- Linear's own sign-in and consent screen, where you hand Claude its access to a workspace. Granted per person, and revocable.
- Approval
- The confirmation Claude waits for in the conversation before it goes ahead with something that changes your workspace.
- MCP
- The open standard connectors are built on: it is what lets an assistant like Claude talk to an outside service such as Linear.
Connect Linear to Claude in three steps
- 01
Find Linear in your connectors
Open Claude's settings, go to Customize then Connectors, and look up Linear in the list. On a Team or Enterprise workspace, an Owner or Primary Owner has to enable it for the organization before members can each sign in.
- 02
Start the connection
Click Connect on the Linear row, then log in to Linear in the window Linear opens itself. If the connection drops or stops responding, Disconnect and connect again; Linear says this does not touch your data.
- 03
Read Linear's consent screen
Check what the screen says the access will cover before you accept. That screen belongs to Linear, not to Claude, and it sets the scope. The access can also be withdrawn later from the Linear side.
The 22 tools, split by what they do
Linear gives Claude 22 tools: 6 that read your account, 5 that change something in it, and 11 no official source describes.
Three groups: what Claude reads, what it changes, and what no official source describes. Tool names stay exactly as Claude shows them.
- 6 read
- 5 write
- 11 not documented
What Claude reads (6)
6 toolsSix tools that find issues, projects and comments without changing them.
list_comments
Reads the comments posted on an issue, which is often where the real decisions and blockers are written down.
get_issue
Opens a single issue so Claude can read that one issue closely, rather than a list, before answering or acting on it.
list_issues
Finds issues across the workspace, the starting point when Claude has to answer a question about a set of tickets rather than one.
list_my_issues
Finds the issues that are yours, the fastest way for Claude to know what is on your plate this week.
list_projects
Finds the projects in your workspace, so Claude can see what is under way before going into a specific one.
get_project
Opens one project in full, giving Claude the material to summarize its scope and where it stands.
What Claude changes (5)
5 toolsFive tools that create or update issues, projects and comments. No source details a confirmation per tool, so the general rule applies.
create_comment
Approval: see the rulePosts a new comment on an issue.
create_issue
Approval: see the ruleAdds a new issue to your Linear workspace, so work discussed in the chat becomes something the team can track.
update_issue
Approval: see the ruleChanges an existing issue so that it reflects what was just decided.
create_project
Approval: see the ruleSets up a new project in Linear, the container into which issues for a larger piece of work can then be grouped.
update_project
Approval: see the ruleEdits a project that already exists, so its information stays in step with what the team decided.
Undocumented (11)
11 toolsLinear describes its tools as a group, not one by one. These eleven names are covered by no official sentence, so we say nothing about what they do.
list_cycles
The directory lists this name, and Linear's documentation only describes its tools as a group covering issues, projects and comments. Nothing official explains this one, so we leave it there.
get_document
Here too the name appears on the directory sheet and in no official description we could find, from Linear or from Anthropic. We would rather flag the gap than guess.
list_documents
A name without an explanation: no official source, neither Linear's documentation nor any Claude page, describes what this tool covers or returns. This page stays silent on its behavior.
list_issue_statuses
Listed by the directory, described by no one. Linear's documentation never goes down to this level of detail, and we will not fill the blank from the tool's name.
get_issue_status
Another entry in the tool list with no sentence attached in any official source. What it does is simply not published.
list_issue_labels
This tool name shows up on the sheet, but no page from Linear or Anthropic tells what it covers. We report the name and stop there.
list_teams
The sheet carries the name, the documentation does not carry an explanation. Linear only speaks of issues, projects and comments when it lists what its tools do.
get_team
One more name the directory lists without any official text behind it. We cannot say more about it without inventing, which this page does not do.
list_users
Present in the list, absent from every description we read. Whatever it returns, no official page spells it out, so neither do we.
get_user
The last of a series of people and team related names with no official description. The name is all we have, and a name is not a description.
search_documentation
This tool appears on the directory sheet, yet Linear's MCP documentation has no line about it. We therefore say nothing about what it searches or returns.
What Claude asks before it changes your workspace
Five documented tools write to Linear, and eleven more are undescribed, so the general rule carries most of the weight here.
By default, Claude stops and asks for your confirmation before any action it takes on an account for you, right in the conversation. No source describes a confirmation specific to a Linear tool, so that default covers creating and updating issues, projects and comments. On Team and Enterprise workspaces, owners decide whether members may let some actions run without a prompt, and they can limit the connector for the whole organization. Anthropic's own example fits Linear exactly: letting Claude view issues while preventing it from creating new ones. Claude also works with your Linear rights and nothing beyond them.
Which plans include the Linear connector
None of the 819 directory sheets states availability by plan, so there is no official connector-by-connector answer, for Linear or any other.
Anthropic's general rule: remote connectors are open to all users on Claude, Cowork, Claude Desktop and mobile, and desktop extensions install on Claude Desktop. On Team and Enterprise, an Owner or Primary Owner enables the connector for the organization before members sign in. Linear's own page describes the setup per plan; that wording is quoted in the limits below. For your account, only the Linear sheet in the directory shows the current state.
What the connector will not do
This connector is documented by its publisher only: no Claude help article or Anthropic developer page covers it, so what follows comes from Linear and the directory.
A connector does not watch your tracker: its tools only run while Claude answers you, never when an issue changes. The directory's verification badge is not a security audit, and Anthropic says on every sheet that it does not choose the tools a publisher exposes. Here the publisher is Linear, which describes its tools in a single sentence rather than one by one. That is why half of the list stays undocumented on this page.
On which plans can Claude use the Linear connector?
- Claude help center, general rule for connectors ↗September 2026Remote connectors are available to all users on Claude, Cowork, Claude Desktop and mobile; on Team and Enterprise, an Owner or Primary Owner enables the connector first.
- Linear MCP documentation ↗read September 2026, undatedLinear lists two setup paths: Team and Enterprise on Claude.ai through the connectors page, Free and Pro on Claude Desktop through Settings then Connectors.
What this page followsLinear describes where to click depending on the plan, not a restriction, and it is the publisher speaking, on an undated page. Anthropic's rule covers all connectors. Neither settles it for your account: check the Linear sheet in the directory on your account.
Need help connecting Linear to Claude?
A person reads every message.
