Productivity & Docs OAuth

Build Your Agent View Linear Documentation

Linear MCP Tools for AI Agents

Let an agent search issues, read project updates, create documents, add comments, and transition work through Linear workflow states.

Available Tools

59 tools available in this integration

Linear.AddComment

Add a comment to an issue.

Linear.AddProjectComment

Add a comment to a project's document content.

Linear.AddProjectToInitiative

Link a project to an initiative.

Linear.ArchiveInitiative

Archive an initiative.

Linear.ArchiveIssue

Archive an issue.

Linear.ArchiveProject

Archive a project.

Linear.CreateDocument

Create a standalone Linear document: a page of markdown such as a spec or a runbook.

Linear.CreateInitiative

Create a new Linear initiative.

Linear.CreateIssue

Create a new Linear issue with validation.

Linear.CreateIssueRelation

Create a relation between two issues.

Linear.CreateLabel

Create a label for issues, projects, or initiatives, and optionally apply it.

Linear.CreateProject

Create a new Linear project.

Linear.CreateProjectStatus

Create a new project status in the Linear workspace.

Linear.CreateProjectUpdate

Create a project status update.

Linear.DeleteLabel

Permanently delete a label.

Linear.GetCycle

Get detailed information about a specific Linear cycle.

Linear.GetDocument

Read a Linear document's content as markdown.

Linear.GetInitiative

Get detailed information about a specific Linear initiative.

Linear.GetInitiativeDescription

Get an initiative's full description with pagination support.

Linear.GetIssue

Get detailed information about a specific Linear issue.

Linear.GetMilestone

Get a milestone by ID or name inside a project.

Linear.GetNotifications

Get the authenticated user's notifications.

Linear.GetProject

Get detailed information about a specific Linear project.

Linear.GetProjectDescription

Get a project's full description with pagination support.

Linear.GetRecentActivity

Get the authenticated user's recent issue activity.

Linear.GetTeam

Get detailed information about a specific Linear team.

Linear.ListAvailableProjectStatuses

List the project statuses a project can be put in, in the Linear workspace.

Linear.ListComments

List comments on an issue.

Linear.ListCycles

List Linear cycles, optionally filtered by team and status.

Linear.ListDocuments

Browse Linear documents, optionally narrowed to the object they are attached to.

Linear.ListInitiatives

List Linear initiatives, optionally filtered by keywords and other criteria.

Linear.ListIssues

List Linear issues, optionally filtered by keywords and other criteria.

Linear.ListLabels

List the labels in the workspace for issues, projects, or initiatives.

Linear.ListMilestones

List milestones in a Linear project.

Linear.ListProjectComments

List comments on a project's document content.

Linear.ListProjectUpdates

List a Linear project's status updates.

Linear.ListProjects

List Linear projects, optionally filtered by keywords, status, team, or creation date.

Linear.ListTeams

List Linear teams, optionally filtered by keywords and other criteria.

Linear.ListWorkflowStates

List available workflow states in the workspace.

Linear.ManageIssueSubscription

Subscribe to or unsubscribe from an issue's notifications.

Linear.ReadAssetContents

Read the bytes behind Linear-hosted 'uploads.linear.app' asset URLs.

Linear.RemoveAttachment

Remove an attachment or external link from a Linear issue, project, or initiative.

Linear.RemoveIssueRelation

Remove the relation (blocks, duplicate, related or similar) between two Linear issues.

Linear.ReplyToComment

Reply to an existing comment on an issue.

Linear.ReplyToProjectComment

Reply to an existing comment on a project document.

Linear.ResolveComment

Resolve or reopen a Linear comment thread by its id.

Linear.RetireLabel

Retire a label, or restore one that was retired.

Linear.SearchDocuments

Full-text search across Linear document titles and body content.

Linear.TransitionIssueState

Transition a Linear issue to a new workflow state.

Linear.TrashDocument

Move a Linear document to the trash — the way to delete or archive one.

Linear.UpdateComment

Update an existing comment.

Linear.UpdateDocument

Edit a Linear document's title, body, or the object it hangs from.

Linear.UpdateInitiative

Update a Linear initiative with partial updates.

Linear.UpdateIssue

Update a Linear issue with partial updates.

Linear.UpdateLabel

Update a label's name, color, description, or group.

Linear.UpdateProject

Update a Linear project with partial updates.

Linear.UpsertAttachment

Attach a URL or a local file to a Linear issue, project, or initiative.

Linear.UpsertMilestone

Upsert a project's milestone.

Linear.WhoAmI

Get the authenticated user's profile and team memberships.

Why agent-optimized tools matter

Built for intent, not API schemas

Ask the agent to "find blocked issues in the current cycle and add a follow-up comment to each." Arcade picks the right Linear tools without guessing issue IDs, team IDs, or cycle IDs.

Up to 100x fewer tokens

Linear list and search calls can return focused issue, project, and document results, so the agent can find the right work before loading descriptions, comments, uploaded assets, or other heavier content.

Complete the workflow end to end

Find an issue, read its details and comments, update its state, add a note, and subscribe to follow-up notifications through one toolkit designed around the complete project task.

Make actions predictable and controlled

Arcade tools return structured results and useful errors across users and runs. Teams can apply scope restrictions, redaction, and approval policies so agents follow the same controls every time.

Securing Linear

The more capabilities agents get, the more useful they are. However, more capabilities bring more risks of undesired effects such as data loss and exfiltration.

This is why Arcade provides you with contextual rules that dictate how and when a tool is allowed to run. Arcade’s contextual access lets you govern tool visibility and behavior at every stage of execution and control who can see a tool, what inputs are allowed, and what comes back.

Learn about Contextual Access Policies

For Linear, you can implement some of these policies:

Access when tools are listed for a user

Hide Linear.ArchiveProject from agents unless the roles your IDP marks as project owners are active, so an agent cannot remove an active project from normal planning views.
Restrict Linear.TrashDocument to agents operating under your workspace-admin role, so unreviewed automation cannot delete specs, runbooks, or other project documentation.
Deny Linear.DeleteLabel to everyone outside the roles your IDP marks as workspace administrators, so an agent cannot permanently remove labels used for triage and reporting.
Hide Linear.RemoveIssueRelation from agents unless the roles your IDP marks as issue owners are active, so routine automation cannot erase dependency or duplicate links.

Pre-execution before each tool call

Require human approval before Linear.TransitionIssueState changes an issue to a completed or canceled state, so an agent cannot close work without review.
Block Linear.CreateIssue when the title or description contains credentials, access tokens, or customer data, so an agent cannot publish secrets in your issue tracker.
Require human approval before Linear.AddComment posts to an issue, so an agent cannot send unreviewed commitments or status claims to collaborators.
Require human approval before Linear.RemoveIssueRelation runs on a blocking relation, so an agent cannot remove a dependency that still governs delivery.

Post-execution after the tool returns

Redact Linear.ReadAssetContents results that contain credentials, access tokens, private keys, or customer records before the model sees file contents.
Strip phone numbers, personal email addresses, and API secrets from Linear.GetDocument results before they reach the model.
Deny Linear.SearchDocuments results for documents marked confidential or subject to legal hold, so protected specifications and investigations are not exposed to the model.

How to use Linear with your agent

Connect Linear to your MCP client with managed per-user OAuth, then follow the setup from authorization through your first agent request.

Your questions, answered

A Linear MCP server exposes Linear capabilities as structured tools an AI agent can call through the Model Context Protocol. After a user authorizes their Linear account, the agent can search issues, read project documents, update work, and perform other permitted actions.

Linear's own MCP server, where available, is Linear's endpoint for accessing its capabilities. Arcade adds a runtime with per-user OAuth, agent-optimized tools, approval workflows, redaction, and scope controls that work consistently across agents and clients.

Arcade agents can search and read issues, projects, initiatives, cycles, milestones, teams, documents, comments, notifications, and activity. They can also create and update issues, documents, projects, initiatives, labels, milestones, comments, relations, attachments, and project updates; transition or archive work; manage subscriptions; and perform other listed write or destructive actions.

Arcade requests the Linear OAuth permissions required by the actions you enable. Read-only workflows need access to read the relevant workspace data, while creating, updating, archiving, deleting, or moving content requires the corresponding write or destructive permissions granted by the user's Linear account.

Yes. Each user authorizes their own Linear account through OAuth. Actions run under that user's authorization, so the agent can access only the workspace data and permissions that user has approved.

Yes. Contextual Access policies can require human approval before consequential Linear actions such as archiving an issue or project, deleting a label, trashing a document, or removing a relation. The call proceeds only after the policy's conditions have been satisfied.

Arcade proxies Linear API calls and does not persist your content as part of normal tool execution. OAuth credentials are brokered and stored encrypted at rest, and the model never receives raw credentials.

Any framework or client that can connect to Arcade's MCP gateway or tool APIs works, including LangChain, OpenAI Agents, CrewAI, Claude Desktop, Claude Code, Cursor, Visual Studio Code, Microsoft Copilot Studio, and GitHub Copilot.

Arcade refreshes access while the user's Linear authorization remains valid. If it is revoked, rotated, or can no longer be refreshed, calls stop until the user reconnects Linear.

Linear's API rate limits and workspace-level quotas still apply to actions performed through Arcade. The available details do not specify a separate Arcade quota or a fixed per-call limit for Linear.

Available Tools

Why agent-optimized tools matter

Built for intent, not API schemas

Up to 100x fewer tokens

Complete the workflow end to end

Make actions predictable and controlled

Securing Linear

How to use Linear with your agent

Your questions, answered

What is a Linear MCP server?

How is Arcade different from Linear's own MCP server?

What Linear actions can Arcade agents perform?

Which Linear permissions does Arcade require?

Does each user connect their own Linear account?

Can I require approval before an agent takes a consequential Linear action?

Does Arcade store Linear data or credentials?

Which AI frameworks and MCP clients work with Arcade Linear?

What happens when Linear authorization expires or is revoked?

What Linear rate limits and quotas apply?

Ready to actually ship your agent?