Files
next-ai-draw-io/packages/mcp-server/README.md
T
dayuan.jiang f257d8ee99 fix(mcp-server): review fixes for the shell page
- a download button in the header opens the web app's export dialog
  (.drawio, .png, .svg, .drawio.svg), which the classic page had and the
  shell lacked when it became the default
- the shell asks draw.io for the custom library menu (libraries=1), as
  the classic page did; the web app keeps libraries=0
- the newest card no longer shows "Rendering preview" for good: the sync
  takes the thumbnail of a diagram the server recovered from its file
  (saved without pictures) while the canvas kept it, and of a write whose
  picture was skipped because an edit came first, once the canvas shows
  the write again
- e2e: the get_selection test covers a shape in a container the user
  entered; a download test saves a .drawio file
2026-10-11 20:56:07 +09:00

274 lines
16 KiB
Markdown

# Next AI Draw.io MCP Server
MCP (Model Context Protocol) server that enables AI agents like Claude Desktop and Cursor to generate and edit draw.io diagrams with **real-time browser preview**.
**Self-contained**: the embedded HTTP server and the draw.io editor are in the package, so after install the preview works offline.
## Quick Start
```json
{
"mcpServers": {
"drawio": {
"command": "npx",
"args": ["@next-ai-drawio/mcp-server@latest"]
}
}
}
```
## Installation
### Claude Desktop
Add to your Claude Desktop config (`~/Library/Application Support/Claude/claude_desktop_config.json` on macOS):
```json
{
"mcpServers": {
"drawio": {
"command": "npx",
"args": ["@next-ai-drawio/mcp-server@latest"]
}
}
}
```
### VS Code
Add to your VS Code settings (`.vscode/mcp.json` in workspace or user settings):
```json
{
"mcpServers": {
"drawio": {
"command": "npx",
"args": ["@next-ai-drawio/mcp-server@latest"]
}
}
}
```
### Cursor
Add to Cursor MCP config (`~/.cursor/mcp.json`):
```json
{
"mcpServers": {
"drawio": {
"command": "npx",
"args": ["@next-ai-drawio/mcp-server@latest"]
}
}
}
```
### Cline (VS Code Extension)
1. Click the **MCP Servers** icon in Cline's top menu bar
2. Select the **Configure** tab
3. Click **Configure MCP Servers** to edit `cline_mcp_settings.json`
4. Add the drawio server:
```json
{
"mcpServers": {
"drawio": {
"command": "npx",
"args": ["@next-ai-drawio/mcp-server@latest"]
}
}
}
```
### Claude Code CLI
```bash
claude mcp add drawio -- npx @next-ai-drawio/mcp-server@latest
```
### Other MCP Clients
Use the standard MCP configuration with:
- **Command**: `npx`
- **Args**: `["@next-ai-drawio/mcp-server@latest"]`
## Usage
1. Restart your MCP client after updating config
2. Ask the AI to create a diagram:
> "Create a flowchart showing user authentication with login, MFA, and session management"
> "Read docs/architecture.md and draw the system as a diagram"
3. The diagram appears in your browser in real-time!
## Features
- **Real-time Preview**: Diagrams appear and update in your browser as the AI creates them. The preview is the web app's canvas: a change the AI makes to the page on screen is outlined, and one Ctrl+Z takes it back
- **Selection**: Select shapes in the preview and say "move these" or "connect this box to that one"; the AI reads what you selected with `get_selection`
- **Drawing Rules**: The AI gets the same layout, edge and style rules as the web app, plus the shape library docs (AWS, Azure, GCP, Kubernetes, Cisco and more), so it uses real icon names instead of guessing
- **Self-check**: The AI can take a screenshot of the rendered diagram (`screenshot: true` on `create_new_diagram` or `edit_diagram`, or `screenshot_diagram`) and fix overlapping shapes or edges that cross shapes
- **Draw from Your Files**: ask the AI to draw from a document, image or web page; it reads the source with the host's own tools and draws. Existing .drawio files open with load_diagram
- **Edit Support**: Modify existing diagrams with natural language instructions. If any change in an edit fails, nothing is written and the AI gets the reason and the current page XML
- **Your Edits Are Kept**: Changes you make in the browser are read before the AI edits again. If the AI overwrites a change you were still making, your version is saved in History
- **Version History**: The last 20 versions appear as cards next to the canvas, with a thumbnail and what changed. Restore one, undo and redo the latest, or compare a version with the canvas; or ask the AI to undo (`restore_version`)
- **Export**: Save as `.drawio`, `.png`, `.svg`, or `.drawio.svg` (an SVG with the diagram embedded, which draw.io and `load_diagram` can open again) through `export_diagram`, or from the download button in the preview's header
- **Multi-page**: List, add, rename, and delete pages, and edit any page
- **Auto-save**: Each session's diagram is saved to `~/.next-ai-drawio/<session-id>.drawio`, and its last 20 versions to `<session-id>.history.json`, so the diagram, History and undo survive a restart of the MCP client
- **Custom Instructions**: keep your own drawing rules in `~/.next-ai-drawio/instructions.md` (for example "Always draw in minimal style"); they are appended to the drawing guide on every call
- **Themes and Dark Mode**: Pick a draw.io theme under **Extras > Theme**; the button at the top right switches the page and the editor between light and dark (the system setting until you choose). `DRAWIO_UI`, `DRAWIO_DARK` and `DRAWIO_LANG` fix them
- **Self-contained**: The draw.io editor ships inside the package and is served from the preview's own origin, so after install the preview works offline. `DRAWIO_BASE_URL` points it at another draw.io instead
## Available Tools
| Tool | Description |
|------|-------------|
| `start_session` | Opens browser with real-time diagram preview; the result includes the drawing rules. Pass `session_id` to continue a saved diagram |
| `list_saved_diagrams` | List the auto-saved diagrams of earlier sessions, newest first, with their pages |
| `get_drawing_guide` | Return the drawing rules again, for example after a long conversation was compacted, or, with `topic`, a short XML reference for tables, layers or groups |
| `get_shape_library` | Return the shapes and icon styles of a library such as `aws4`, `azure2`, or `kubernetes` |
| `create_new_diagram` | Create a new diagram from XML; a plain list of `mxCell` elements is enough |
| `load_diagram` | Load a `.drawio` or `.drawio.svg` file into the session, from a `path` on disk or from its `xml` content (handles compressed files) |
| `edit_diagram` | Edit diagram by ID-based operations (update/add/delete cells); all or nothing |
| `get_diagram` | Get the current diagram XML, including your edits in the browser |
| `get_selection` | Return the shapes and edges you selected in the preview (ids, labels, positions), so the AI can act on "these" |
| `screenshot_diagram` | Return a PNG of a page so the AI can check the rendered diagram |
| `export_diagram` | Save diagram to a `.drawio`, `.png`, `.svg`, or `.drawio.svg` file |
| `list_pages` | List every page (tab) with id, name, index, and cell count |
| `add_page` | Append a new page without touching existing ones |
| `rename_page` | Rename a page |
| `delete_page` | Delete a page (refuses to delete the last one) |
| `restore_version` | Undo: put an earlier version from History back on the canvas; the current one is kept, so a redo is possible |
## Continue a Diagram Later
After every change, the diagram is saved as a normal `.drawio` file in `~/.next-ai-drawio/`, named after the session id (for example `mcp-mgd0a1b2-x7k2p1.drawio`). `start_session` tells the AI both the id and the file path.
To continue a diagram in a later conversation (for example after `claude --resume`, or in a new chat), the AI calls `start_session` with `session_id` set to that id: the same preview URL opens, the saved diagram is shown, and auto-save keeps writing to the same file. If the id is no longer in the conversation, `list_saved_diagrams` returns every saved diagram, newest first, with the names and cell counts of its pages, so you can ask for "the architecture diagram from yesterday" and let the AI pick it. `load_diagram` with the file path still works too, and you can open the file in draw.io yourself.
History comes back with the diagram: the last 20 versions are saved next to it in `<session-id>.history.json` (without thumbnails). When the AI continues the session with `start_session` and its `session_id`, or a preview tab is still open after a restart, the version cards show them again and `restore_version` can undo to them.
The newest 50 files are kept, each with its History file. Set `DRAWIO_DATA_DIR` to use another folder, or to `off` to turn auto-save off.
## Custom Instructions
To give the AI your own drawing rules, write them in `~/.next-ai-drawio/instructions.md` as Markdown, for example "Always draw in minimal style" or "Label every edge". The file is appended to the drawing guide under a `## Custom Instructions` heading each time the guide is returned (`start_session`, `get_drawing_guide` and the `diagram-workflow` prompt), so edits apply without restarting your MCP client. Only the first 5000 characters are used.
`DRAWIO_DATA_DIR` changes the folder the file is read from; with `DRAWIO_DATA_DIR=off` the default folder is still used, since the file is only read. The text reaches the model as it is, so keep it to drawing rules you trust.
## How It Works
```
┌─────────────────┐ stdio ┌─────────────────┐
│ Claude Desktop │ <───────────> │ MCP Server │
│ (AI Agent) │ │ (this package) │
└─────────────────┘ └────────┬────────┘
│
┌────────▼────────┐
│ Embedded HTTP │
│ Server (:6002) │
└────────┬────────┘
│
┌────────▼────────┐
│ User's Browser │
│ (draw.io embed) │
└─────────────────┘
```
1. **MCP Server** receives tool calls from Claude via stdio
2. **Embedded HTTP Server** serves the preview page and the draw.io editor, and handles state
3. **Browser** shows real-time diagram updates via polling
The server listens on `127.0.0.1` only. Every `/api` request must carry a token that the server generates at start and writes into the preview page, so another website open in the same browser cannot read or change the diagram; the preview page also refuses to be embedded in other pages. Opening the preview URL in another browser on the same machine works, since the page comes with the token.
## Configuration
| Variable | Default | Description |
|----------|---------|-------------|
| `PORT` | `6002` | Port for the embedded HTTP server |
| `DRAWIO_BASE_URL` | unset (the bundled draw.io) | An external draw.io for the preview, such as a self-hosted instance (see below). The page cannot reach into an editor from another origin, so with it the AI's changes are not outlined, Ctrl+Z does not take them back and `get_selection` cannot read the selection. The version cards and everything else keep working. |
| `DRAWIO_DATA_DIR` | `~/.next-ai-drawio` | Folder for the auto-saved `.drawio` files and your `instructions.md`. Set to `off` to turn auto-save off (`instructions.md` is then read from the default folder). |
| `DRAWIO_LANG` | unset | Language of the draw.io editor and of the preview's own texts. Unset, the preview's texts follow the browser language, and draw.io chooses: English on the bundled copy until the user picks one under **Extras > Language**, the browser language on `embed.diagrams.net`. A code such as `en`, `zh`, `zh-tw`, `ja` or `de` fixes both and hides that submenu. |
| `DRAWIO_UI` | unset | draw.io theme. Unset, the user picks one under **Extras > Theme** and draw.io remembers it. `kennedy`, `atlas`, `dark`, `min`, `sketch` or `simple` fixes the theme and hides that menu. |
| `DRAWIO_DARK` | `auto` | Dark mode of the preview and the editor until the user switches it with the button at the top right (the browser remembers that choice): `auto` follows the system, `1` starts dark, `0` starts light. |
| `DRAWIO_PREVIEW_UI` | `shell` | The preview page `start_session` opens. `classic` opens the previous preview page (see [Classic preview page](#classic-preview-page)). |
| `DRAWIO_AUTO_SCREENSHOT` | unset | Set to `true` to attach a screenshot to every `create_new_diagram` and `edit_diagram` result, so the AI checks each drawing. Costs 2 to 10 s per call; the preview tab must be open and in front. A call can still pass `screenshot: false`. |
| `BROWSER` | unset | Set to `none` and `start_session` does not open the preview in the system browser (the convention of Vite and Create React App dev servers); the result still names the URL. |
| `DEBUG` | unset | Set to `true` to log debug messages to stderr. |
### Private Deployment (Self-hosted draw.io)
For security-sensitive environments that require private deployment of draw.io:
```json
{
"mcpServers": {
"drawio": {
"command": "npx",
"args": ["@next-ai-drawio/mcp-server@latest"],
"env": {
"DRAWIO_BASE_URL": "https://drawio.your-company.com"
}
}
}
}
```
You can deploy your own draw.io instance using the official Docker image:
```bash
docker run -d -p 8080:8080 jgraph/drawio
```
Then set `DRAWIO_BASE_URL=http://localhost:8080` (or your server's URL). The preview page loads nothing else from the internet, so with a local draw.io it works offline. One exception: shapes from the Material Design library show icons from `fonts.gstatic.com`.
With an external draw.io the preview cannot reach into the editor (browsers keep pages and frames from other origins apart), so the AI's changes are not outlined on the canvas, Ctrl+Z does not take them back (use the version cards or `restore_version`), and `get_selection` cannot read what you selected. `start_session` tells the AI about this mode.
Without `DRAWIO_BASE_URL` the preview uses the trimmed draw.io copy bundled with this package. It has the editor, the shape libraries, the templates, PlantUML and Mermaid; features that load more code when used (the org chart layout, for example) are not included. Set `DRAWIO_BASE_URL` to a full draw.io if you need them.
Like the web app's bundled copy, it has no image proxy (`/drawio/proxy`): images from other websites, including the avatars in the Org Chart and Mind Map templates and the Arista icons in the network templates, show on the canvas only when online and are left out of PNG and SVG exports and version thumbnails. Insert such images from a file instead, or set `DRAWIO_BASE_URL` to a full draw.io (the `jgraph/drawio` Docker image includes the proxy). See [Offline deployment](https://github.com/DayuanJiang/next-ai-draw-io/blob/main/docs/en/offline-deployment.md).
### Classic preview page
`DRAWIO_PREVIEW_UI=classic` opens the preview page of the previous releases: draw.io with a **History** dialog and a **Download** button, without the outline of the AI's changes, Ctrl+Z for them, the version cards, Compare and `get_selection`. It stays for one more release and is then removed.
## Troubleshooting
### Port already in use
If port 6002 is in use, the server will automatically try the next available port (up to 6020).
Or set a custom port:
```json
{
"mcpServers": {
"drawio": {
"command": "npx",
"args": ["@next-ai-drawio/mcp-server@latest"],
"env": { "PORT": "6003" }
}
}
}
```
### "No active session"
Call `start_session` first to open the browser window.
### Browser not updating
Check that the browser URL has the `?mcp=` query parameter. The MCP session ID connects the browser to the server.
### Screenshot or PNG/SVG export times out
PNG and SVG files are rendered by draw.io in the preview tab. Browsers slow down tabs that stay in the background, so the tab may not answer in time. Bring the preview tab to the front and try again.
### Preview is blank inside VS Code Simple Browser
The preview page refuses to be embedded in other pages (it sends `Content-Security-Policy: frame-ancestors 'self'`), so in-editor browsers such as VS Code Simple Browser, Cursor's built-in browser or a port forward's "Preview in Editor" show a blank page. Open the Browser URL from the `start_session` result in a regular browser (Chrome, Edge, Firefox, Safari) instead.
## License
Apache-2.0