Umlout MCP Server
Hosted MCP server that lets AI assistants create and edit diagrams (UML, flowcharts, wireframes, domain models) in a Umlout workspace via natural language.
README
Umlout MCP Server
Let your AI assistant draw on a real whiteboard.
Umlout exposes a hosted Model Context Protocol server, so Claude, Cursor, VS Code Copilot and any other MCP client can create and edit diagrams in your Umlout workspace — UML class and sequence diagrams, flowcharts, activity diagrams, wireframes and domain models.
Nothing to install and nothing to run: the server is hosted at https://www.umlout.com/mcp/sse.
You only need an API key.
Quick start
1. Get an API key. Sign in at umlout.com, open Profile → MCP API Keys, and create a key.
2. Add the server to your client.
<details open> <summary><b>Claude Code</b></summary>
claude mcp add --transport sse umlout https://www.umlout.com/mcp/sse --header "Authorization: Bearer YOUR_API_KEY"
More options, including project scope: examples/claude-code.md. </details>
<details> <summary><b>Cursor</b> · <b>VS Code</b> — clients that speak remote SSE natively</summary>
~/.cursor/mcp.json:
{
"mcpServers": {
"umlout": {
"url": "https://www.umlout.com/mcp/sse",
"headers": { "Authorization": "Bearer YOUR_API_KEY" }
}
}
}
For VS Code Copilot use examples/vscode.json — it prompts for the key and keeps it in VS Code's secret storage instead of a committed file. </details>
<details> <summary><b>Claude Desktop</b> — via the <code>mcp-remote</code> bridge</summary>
Claude Desktop's config file does not take a remote URL directly, so route it through
mcp-remote (needs Node.js). Edit
~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or
%APPDATA%\Claude\claude_desktop_config.json (Windows):
{
"mcpServers": {
"umlout": {
"command": "npx",
"args": [
"-y", "mcp-remote", "https://www.umlout.com/mcp/sse",
"--header", "Authorization: Bearer YOUR_API_KEY"
]
}
}
}
Then quit Claude Desktop completely and reopen it — closing the window is not enough. </details>
3. Ask for a diagram:
Draw a UML sequence diagram of an OAuth2 authorization code flow on a new board called "Auth".
Verify your setup at any time:
python3 scripts/check_connection.py --api-key YOUR_API_KEY
What it can do
37 tools across four areas, plus 4 read-only resources. Full reference with every argument: docs/tools.md and docs/resources.md.
| Area | What the assistant can do |
|---|---|
| Diagrams | Create, list, find, rename, clear and delete boards |
| Shapes & connections | Add and edit shapes, draw connections with UML notation, place sequence messages, define custom anchor points, bulk-create hundreds of elements in one call |
| Domain models | Build nestable folders → elements → relations; create a whole model tree in a single call |
| Comments | Add, list, resolve and delete comments and replies on any element |
The shape vocabulary covers 70 types — basic geometry, UML class/interface/package, sequence (actor, lifeline, activation, fragment), activity (action, decision, fork/join, swimlanes), and a full wireframe kit (screens, buttons, inputs, navbars, tables, cards).
Things worth asking for
- "Turn this OpenAPI spec into a component diagram."
- "Sketch the mobile onboarding flow as wireframes — three screens."
- "Read the board 'Checkout' and tell me which states have no outgoing transitions."
- "Build a domain model from these requirements: orders, invoices, customers."
Authentication and limits
Every request carries your key in Authorization: Bearer <key> (or X-API-Key). Keys are scoped
to your account — the assistant sees exactly the diagrams you can see, and nothing else.
| Limit | Value |
|---|---|
| Requests | 60 per minute |
| Write tool calls | 600 per hour |
Bulk write calls (bulk_*) |
60 per hour |
Details, key rotation and revocation: docs/authentication.md. Something not working? docs/troubleshooting.md.
About this repository
This repo is the public home of the Umlout MCP connector: documentation, client configs, the registry manifest (server.json) and a connection checker. The server itself is a hosted service — there is no local installation, so there is no server source here.
Issues and questions about the MCP integration are welcome in Issues.
License
MIT — documentation and examples.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。