Draw.io
Integrates Draw.io's diagramming capabilities with AI agents, enabling programmatic diagram control and analysis.
Draw.io MCP server
Let's do some Vibe Diagramming with the most wide-spread diagramming tool called Draw.io (Diagrams.net).
Key Highlights
- Built-in Draw.io editor - no browser extension required
- MCP server that lets AI agents control Draw.io diagrams
- Programmatic diagram creation, inspection, and modification via MCP tools
- Layer management for complex diagrams
- Works with any MCP client (Claude Desktop, Claude Code, Zed, Codex, etc.)
Introduction
The Draw.io MCP server brings Draw.io diagramming capabilities to AI agents. It provides MCP tools that can create, read, update, and delete diagram elements - letting AI assistants build architectural diagrams, flowcharts, and visual documentation automatically.
Two ways to use:
- Built-in editor - Server hosts Draw.io directly, accessible in your browser
- Browser extension - Connect to Draw.io running in your browser via extension
Requirements
- Node.js (v20 or higher) - Runtime environment for the MCP server
- MCP client - Claude Desktop, Claude Code, Zed, Codex, OpenCode, or any MCP-compatible host
For Built-in Editor
No additional requirements - runs out of the box with --editor flag.
For Browser Extension
- Browser extension - drawio-mcp-extension
- Draw.io open in your browser
Optional
- pnpm - Preferred package manager (npm works fine too)
Quick Start
1. Configure your MCP host
Add the server to your MCP client configuration:
Claude Desktop
Edit ~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"drawio": {
"command": "npx",
"args": ["-y", "drawio-mcp-server", "--editor"]
}
}
}
Claude Code
claude mcp add-json drawio '{"type":"stdio","command":"npx","args":["-y","drawio-mcp-server","--editor"]}'
Zed
Add to ~/.config/zed/settings.json:
{
"context_servers": {
"drawio": {
"command": "npx",
"args": ["-y", "drawio-mcp-server", "--editor"],
"env": {}
}
}
}
Codex
Edit ~/.codex/config.toml:
[mcp_servers.drawio]
command = "npx"
args = ["-y", "drawio-mcp-server", "--editor"]
OpenCode
Add to opencode.json in your project root or ~/.config/opencode/opencode.json:
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"drawio": {
"type": "local",
"command": ["npx", "-y", "drawio-mcp-server", "--editor"],
"enabled": true
}
}
}
For other MCP clients and detailed configuration (including pnpm options), see Configuration.
2. Open the editor
After restarting your MCP host, open: http://localhost:3000/
3. Start diagramming
Example prompts you can try:
"Create an event-driven architecture diagram showing a message queue with producers, consumers, and three backend services"
"Draw a CRUD API diagram with a database, API gateway, and four microservices with their endpoints"
"Add a new layer called 'Background' and move all decorative elements to it, then create a new layer for annotations"
Your AI assistant can now control the diagram using MCP tools.
Features
The server provides MCP tools for:
- Diagram inspection - read shapes, layers, and cell properties
- Diagram modification - add/edit/delete shapes, edges, and labels
- Layer management - create, switch, and organize layers
See Tools Reference for the complete list of available tools.
Installation
The server runs as part of your MCP host. Detailed configuration for all supported clients (Claude Desktop, Claude Code, Zed, Codex, oterm) including npm and pnpm options is available in Configuration.
Alternative: Browser Extension
Instead of the built-in editor, you can use the browser extension to connect to Draw.io running in your browser. This works with or without the --editor flag.
- Open Draw.io in your browser
- Install the Draw.io MCP Browser Extension:
- Ensure the extension is connected (green signal overlay on icon)
Configuration without --editor:
{
"mcpServers": {
"drawio": {
"command": "npx",
"args": ["-y", "drawio-mcp-server"]
}
}
}
See the extension documentation for more details.
Related Resources
Configuration - CLI flags and advanced options
Tools Reference - Complete MCP tools documentation
Star History
Assessments
เซิร์ฟเวอร์ที่เกี่ยวข้อง
WordPress MCP Server
A secure bridge between AI assistants and WordPress, enabling site management and content operations through natural language.
Linear MCP Server
An MCP server for interacting with the Linear API, allowing AI agents to manage issues, projects, and teams.
JIRA
Access and manage JIRA issues, projects, and users with optimized data payloads for AI context windows.
Agile Luminary
Connects AI clients to the Agile Luminary project management system via its REST API.
Excel MCP Server
Manipulate Excel files (XLSX, XLSM, etc.) without needing Microsoft Excel, featuring an integrated AI assistant.
MetaTrader MCP Server
A Python-based MCP server that allows AI LLMs to execute trades on the MetaTrader 5 platform.
Google Sheets
A server that connects to the Google Sheets API, enabling AI-driven spreadsheet automation and data manipulation.
Research MCP Server
A research server that retrieves and creates survey data pages in Notion.
Deck Builder MCP
Create and manipulate PowerPoint presentations programmatically using JSON or Markdown.
MCP Data Analizer
Analyze and visualize data from .xlsx and .csv files using matplotlib and plotly.
