Arlet
Linear

Connect Linear to Copilot Studio

Search, read and write Linear from Copilot Studio. Arlet links the two through one MCP connection and takes care of keys and authentication.

Enable Linear in ArletCopilot Studio connection guide (docs)

Arlet makes Linear's official MCP server available from the AI client you already use. There is no OAuth application to create on the Linear side. Signing in completes the connection.

The AI can search, create and update issues and projects, and read and write comments. The available tools are exactly those provided by Linear's official server. If you work across several workspaces, each can be added as its own connection.

How to connect Linear to Copilot Studio

  1. 1

    In the Arlet dashboard, open Integrations → Add an integration and choose Linear. Sign in with Link Linear, name the connection and click Create.

  2. 2

    Sign in to Copilot Studio with your work account, create a new agent (or open an existing one), and in the Build tab choose Tools → + → Add → Model Context Protocol (MCP) in the right panel.

  3. 3

    In the Add MCP server form, enter "Arlet" as the Server name, https://mcp.arlet.dev/mcp/ as the Server URL, choose OAuth 2.0 for Authentication and "Dynamic (detected)" for Configuration type, then click Add. No Client ID / Secret is needed.

  4. 4

    On the Select a connection screen, choose Create new connection → Create, then sign in with Google on the Arlet authorization screen and click Allow. Click Add to attach the tool to the agent, then Publish to use it from Microsoft 365 Copilot.

Requires a Microsoft work account and a Copilot Studio license (or trial). MCP is available only for agents using generative orchestration and not in Copilot Studio in Teams.

What you can do

Linear tools that Copilot Studio can call.

  • list_issues

    Search and list issues by team, assignee, status, labels and more.

  • get_issue

    Fetch one issue in full, including its description, status, assignee and comments.

  • save_issue

    Create or update an issue. Status changes, assignment and labels all happen here.

  • list_my_issues

    List the issues assigned to you.

  • list_comments

    Read the comments on an issue.

  • create_comment

    Add a comment to an issue.

  • list_projects

    Search and list projects to understand the roadmap.

  • get_project

    Fetch one project in detail (goal, timeline, progress).

  • save_project

    Create or update a project.

  • list_cycles

    List a team's cycles (sprints).

  • list_teams

    List the teams in the workspace.

  • list_users

    List members, for example to assign owners.

  • list_issue_statuses

    List a team's workflow states (Todo, In Progress, Done and so on).

  • list_issue_labels

    List the labels available for issues.

  • list_documents

    List documents attached to projects and other objects.

  • get_document

    Fetch a document's content.

The tool list follows what Linear's official MCP server provides and may change.

Example uses

  • Turn meeting notes into issues

    Pull out decisions and action items and file them as issues with the right team, assignee and labels.

  • Summarize the sprint

    Group the current cycle's issues by status and write a progress report that names the items running late and their owners.

  • Tidy up bug reports

    Rewrite a rough report into steps to reproduce, expected and actual results, check for duplicates, then file it.

  • Answer "when will it ship?"

    Answer questions about a project's timeline by citing the remaining issues and their owners.

Prompts you can use as-is

  • List the issues in the current cycle that have sat in In Progress for more than three days, with assignees
  • Extract the action items from these meeting notes and create issues for the Backend team with owners
  • Group the remaining issues of the "Checkout revamp" project by status and write this week's progress report
  • Rewrite this bug report into steps / expected / actual, and file it with the bug label if there is no similar issue

Use Linear with other AI clients