miro
MCP server for controlling Miro whiteboards with AI assistants
claude mcp add --transport stdio olgasafonova-miro-mcp-server docker run -i ghcr.io/olgasafonova/miro-mcp-server:latest \ --env MIRO_ACCESS_TOKEN="Your Miro access token (boards:read, boards:write)"
How to use
This MCP server exposes a wide set of Miro-related tools as MCP capabilities that you can invoke from any MCP client (Claude, Cursor, VS Code, or other MCP clients). The server reads your Miro board data via the provided access token and exposes operations such as listing boards, reading board content, creating and updating sticky notes, frames, mindmaps, and more, as well as exporting board data and diagrams. With the 88 included tools, you can perform common board management tasks, create and update items (stickies, shapes, images, docs, cards), handle frames and mindmaps, and perform bulk operations. To use it, start the server via your chosen deployment (for example, the Docker image shown in the Quick Start), configure your MCP client to connect to this server, and provide your MIRO_ACCESS_TOKEN so the server can authenticate against the Miro API. Once connected, invoke tools like miro_list_boards, miro_create_sticky, miro_update_item, miro_create_frame, miro_bulk_create, miro_search_board, miro_export_board, and more through your MCP client. The server acts as a bridge between your MCP client and the Miro API, translating MCP tool calls into Miro API requests and returning results back to the client.
How to install
Prerequisites:
- Docker installed and running on your machine or host
- Access token for Miro with boards:read and boards:write permissions
Install and run the MCP server (Docker):
-
Ensure you have Docker installed and running
-
Pull and run the server: docker run -d --name miro-mcp-server -p 8080:8080
-e MIRO_ACCESS_TOKEN=YOUR_TOKEN_HERE
ghcr.io/olgasafonova/miro-mcp-server:latest Replace YOUR_TOKEN_HERE with your actual Miro access token. -
Verify the container is running: docker ps | grep miro-mcp-server
If you prefer a non-Docker method, refer to the repository's setup instructions for alternative installation methods (Homebrew, manual download).
Additional notes
Tips and notes:
- You must provide a valid MIRO_ACCESS_TOKEN with boards:read and boards:write permissions for the server to access and modify boards.
- If you rotate tokens, update the MIRO_ACCESS_TOKEN environment variable and restart the container/service.
- When using 88 tools, familiarize yourself with common actions like creating and updating items, managing frames, and exporting board content for reporting.
- If you encounter authentication or rate-limit errors from the Miro API, verify token scopes and ensure token is not expired or revoked.
- For production deployments, consider securing the server behind TLS and managing tokens securely in your deployment environment.
Related MCP Servers
sandbox
A Model Context Protocol (MCP) server that enables LLMs to run ANY code safely in isolated Docker containers.
storybook
MCP server for Storybook - provides AI assistants access to components, stories, properties and screenshots. Built with TypeScript and Model Context Protocol SDK.
mediawiki
MCP server for MediaWiki wikis - search, read, and edit wiki content from AI assistants
mcp-safe-run
Tired of hardcoding secrets like API keys in your MCP client configuration (e.g., mcp.json, claude_desktop_config.json)? mcp-secure-launcher lets you run your existing MCP servers securely without modifying them.
mcp4go
A comprehensive Go SDK for the Model Context Protocol (MCP) - simplifying AI application development by abstracting away protocol complexities.
mcp-tidy
CLI tool to visualize and manage MCP server configurations in Claude Code. List servers, analyze usage statistics, and clean up unused servers