Arlet
Miro

Connect Miro to Copilot Studio

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

Enable Miro in ArletCopilot Studio connection guide (docs)

Arlet makes Miro's official MCP server available from the AI client you already use. Signing in completes the connection; there is no app to create on the Miro side.

The AI can search boards, read their content, place diagrams and images, reply to comments and create prototypes. The available tools are those provided by Miro's official server, and each connection is bound to one Miro team. Miro's server is in public beta and has a daily tool-call limit per plan.

How to connect Miro to Copilot Studio

  1. 1

    In the Arlet dashboard, open Integrations → Add an integration and choose Miro. Sign in with Link Miro, 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

Miro tools that Copilot Studio can call.

  • board_search_boards

    Search and list the boards you can access.

  • board_create

    Create a new board.

  • canvas_read_as_svg

    Read board items as SVG.

  • canvas_create_from_svg

    Create several board items from SVG.

  • canvas_update_from_svg

    Apply an SVG document as a diff to board items.

  • canvas_get_canvas_composer_skill

    Get the SVG specification for composing board layouts.

  • comment_list_comments

    List comments on a board or an item.

  • comment_reply

    Reply to a comment thread.

  • comment_resolve

    Resolve or reopen a comment thread.

  • image_create

    Place an image on a board.

  • image_get_data

    Get an image item's metadata and data.

  • image_get_upload_url

    Get a temporary URL for uploading an image.

  • prototype_read

    Read prototype screens from a board.

  • prototype_create

    Create a Miro prototype from HTML screens.

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

Example uses

  • Put a discussion on the board

    Turn meeting notes or brainstorm output into sticky notes and frames on a board.

  • Summarize a board

    Read a workshop board and write up the decisions and ideas.

  • Clear comments

    List unresolved comments, reply where needed and resolve them.

  • Draw a diagram

    Describe a workflow or architecture and get it drawn on a board as SVG.

Prompts you can use as-is

  • Split these brainstorm notes into sticky notes on the Q4 Planning board
  • Read the Workshop 9/18 board and list the decisions and ideas
  • List the unresolved comments on the Website Redesign board and resolve the ones already addressed
  • Draw the order-to-shipment workflow as a diagram on a new board

Use Miro with other AI clients