Miro Whiteboard Connector MCP Server

CommunicationTypeScript

Connect to and manipulate Miro whiteboards directly from AI assistants

Available Tools

createSticky

Creates a sticky note on a Miro board

boardIdcontentpositioncolor

createShape

Creates a shape on a Miro board

boardIdtypecontentposition

readBoard

Retrieves information about a Miro board

boardId

readFrame

Retrieves information about a frame on a Miro board

boardIdframeId

getBoardContents

Retrieves all content items from a Miro board

boardId

bulkCreate

Creates multiple items on a Miro board in a single operation

boardIditems

The Miro Whiteboard Connector enables AI assistants to interact with Miro boards, allowing for seamless collaboration between AI and humans in visual workspaces. This integration supports creating and manipulating sticky notes, shapes, and other board elements, as well as reading board contents for analysis. With this connector, you can have your AI assistant create diagrams, organize information, and respond to visual content in Miro boards. It's particularly effective for converting physical sticky notes to digital versions by taking a photo and having the AI recreate them in Miro.

Overview

The Miro Whiteboard Connector allows AI assistants like Claude to interact directly with Miro boards. This enables collaborative workflows where your AI can view, create, and organize content on your Miro boards.

Prerequisites

Before using this connector, you'll need:

A Miro account
A Miro OAuth token (for authentication)
Node.js installed on your system

Installation

Option 1: Install via Smithery (Recommended)

The easiest way to install the Miro Whiteboard Connector is through Smithery:

npx -y @smithery/cli install @llmindset/mcp-miro --client claude

Option 2: Install via mcp-get

You can also install using mcp-get:

npx @michaellatman/mcp-get@latest install @llmindset/mcp-miro

Note: Windows PowerShell users may need to run Set-ExecutionPolicy Bypass -Scope Process before this command.

Option 3: Manual Installation

Clone the repository:

git clone https://github.com/evalstate/mcp-miro.git

Install dependencies:
```
cd mcp-miro
npm install
```
Build the server:
```
npm run build
```
Configure your AI client to use the server (see Configuration section)

Configuration

To use with Claude Desktop, you need to add the server configuration to Claude's config file:

On MacOS: Edit ~/Library/Application Support/Claude/claude_desktop_config.json

On Windows: Edit %APPDATA%/Claude/claude_desktop_config.json

Add the following configuration, replacing the paths and token with your own:

{
  "mcpServers": {
    "mcp-miro": {
      "command": "/path/to/node",
      "arguments": [
        "/path/to/mcp-miro/build/index.js",
        "--token", "YOUR-MIRO-OAUTH-KEY"
      ]
    }
  }
}

Obtaining a Miro OAuth Token

Go to the Miro Developer Portal
Create a new app or use an existing one
Configure the app permissions to include board access
Generate an OAuth token for your account

Usage Examples

Once configured, you can ask Claude to perform various operations on your Miro boards:

"Create a new sticky note on my Miro board with the text 'Project Ideas'"
"Read the contents of my current Miro board"
"Create a flowchart diagram on my Miro board based on this process..."
"Take this photo of sticky notes and recreate them on my Miro board"

Troubleshooting

If you encounter issues:

Verify your Miro OAuth token is valid and has the necessary permissions
Check the Claude Desktop logs for any error messages
Try running the MCP Inspector for debugging:
```
npm run inspector
```

Development

For development with auto-rebuild:

npm run watch