Miro MCP

📘

This is a beta release of our MCP: sign up at https://miro.com/ai/mcp/.

It is intended for evaluation and feedback purposes. The feature set and user experience may change in future releases.

Connect your AI tools to Miro using the Model Context Protocol (MCP), an open standard that enables AI assistants to query data, trigger actions, and access real-time context in your Miro boards.

What can you do with Miro MCP?

📘

With Miro MCP, we currently support two use cases but we are working on supporting more use cases, so stay tuned for updates.

1. Generate diagrams based on:

   • Code repositories
   • Text descriptions
   • GitHub URLs
   • Product requirement documents (PRD)

   Miro MCP quickly adds the diagram to your board and helps visualize complex structures.

2. Generate code based on Miro board content:

   • Convert PRDs into working code.
   • Transform diagrams into application structure.
   • Use prototypes as implementation guides.
   • Leverage board context for precise code generation.

What is Miro MCP?

Miro MCP is our hosted server that gives AI tools secure access to the Miro boards within your organization. It enables AI assistants to read board context, create diagrams, and generate prototypes while maintaining enterprise-grade security.

Security and Authentication

• OAuth 2.1 — Secure authorization with dynamic client registration.
• Enterprise Security — Compliant with enterprise security standards.
• Rate Limiting — Protected against overuse with standard API request limits.

Supported Integrations

Miro MCP works with popular AI tools that support MCP clients:

• Cursor
• Claude Code
• OpenAI Codex
• VSCode and GitHub Copilot
• Gemini CLI
• Windsurf
• Kiro
• Glean
• Devin
• Lovable

Why use Miro MCP?

• Secure access — Enterprise-grade security with OAuth 2.1 authentication.
• Full workspace access — AI tools can read and write to your Miro boards just like you can.
• Optimized for AI — Built specifically for AI agents with efficient data formatting.