miro-mcp

# Miro MCP Integration

## Quick Start

Miro MCP enables AI agents to read from and write to Miro boards via the Model Context Protocol—an open standard for AI-external system integration. Your agent can generate diagrams, analyze board content, and create code from visual designs.

**Prerequisites:**
- MCP-capable client (Cursor, Claude Code, Replit, Lovable, VSCode, etc.)
- OAuth 2.1 support in your client
- Active Miro workspace access

**Minimal Setup:**
1. Add MCP configuration: `url: https://mcp.miro.com/`
2. Click "Connect" and authenticate via OAuth 2.1
3. Select your Miro team during OAuth flow
4. Start prompting with board URLs

**Quick Example:**
```
Prompt: "Summarize the content on this board: https://miro.com/app/board/uXjVGAeRkgI=/"
Result: Agent reads board items and returns a summary
```

See [references/mcp-connection.md](references/mcp-connection.md) for detailed setup instructions per client.

## Core Capabilities

Miro MCP supports two primary use cases: **diagram generation** and **code generation**.

### Diagram Generation

Generate visual diagrams directly on Miro boards from code, PRDs, or text descriptions:
- **From Code:** Provide repository URLs or code snippets → agent generates architecture/data flow diagrams (UML, flowchart, ERD)
- **From PRDs:** Share product requirement documents → agent creates visual workflows, user flows, state diagrams
- **From Text:** Describe a system → agent visualizes it as architecture or sequence diagram
- **From GitHub URLs:** Agent analyzes GitHub repos and generates architectural diagrams

Tool: Use `code_explain_on_board` prompt or `diagram_create` tool with DSL (flowchart, UML class/sequence, ERD).

### Code Generation

Generate working code from board content:
- **PRD to Code:** Board contains product requirements → agent generates documentation + implementation guidance
- **Diagram to Code:** Architecture diagram on board → agent generates code structure matching the design
- **Prototype to Code:** P...