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.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.