Uml MCP Server

Generate UML and other diagrams through the [Model Context Protocol](https://modelcontextprotocol.io/).

Remote serverstreamable-httpPython

What is the Uml MCP MCP server?

If you want an AI assistant working directly with Uml MCP, the uml mcp mcp server is the bridge. Generate UML and other diagrams through the Model Context Protocol.

What Uml MCP does

Generate UML and other diagrams through the Model Context Protocol.

Tools it exposes

Once connected, the assistant can call these 7 tools directly:

  • generate_uml — Render a diagram; omit output_dir for URL/base64 only
  • validate_uml — Structural validation before render; strict enables extra Mermaid/D2 checks
  • list_diagram_types — Same metadata as uml://types when resources are awkward
  • generate_uml_batch — Multiple diagrams in one call (cap: MCP_BATCH_MAX_ITEMS)
  • Tools — The Tools tool exposed by this server
  • Vercel — 1. Connect the repo to Vercel 2. Use https://.vercel.app/mcp 3. Keep /mcp in all MCP client URLs
  • Smithery — 1. Open smithery.ai/new, choose URL 2. Enter https://.vercel.app/mcp 3. Configure display name, description, and

Installing the uml mcp mcp server

Setup follows the standard MCP pattern: clone or install the server, then register it in your client's configuration file and restart the client. The configuration snippets on this page cover Claude Desktop, Claude Code and Cursor.

Where it fits

Cloud and DevOps servers put infrastructure on speaking terms with your assistant, so "why is this broken?" is answered from real state rather than a generic checklist. Uml MCP sits in that group, and the shape of its toolset — generate_uml, validate_uml, list_diagram_types among others — tells you what it is really for. Worth comparing against the other cloud devops servers in this directory before you commit to one, since several overlap in scope but differ sharply in setup cost and permissions.

Practical notes

  • This is a hosted server — you point your client at an endpoint rather than running a local process, so there is nothing to keep updated on your machine.
  • With 7 tools exposed, expect a noticeable bump in prompt size — disable it in projects that never use Uml MCP.
  • Maintained by antoinebou12, written in Python.
  • MCP clients ask for confirmation before each tool call by default. Keep that on while you learn what the uml mcp mcp server actually does with your data.
  • Every entry in this directory is reviewed by hand before it goes live, and details are checked against the project's own documentation.

Available tools

ToolWhat it does
generate_umlRender a diagram; omit output_dir for URL/base64 only
validate_umlStructural validation before render; strict enables extra Mermaid/D2 checks
list_diagram_typesSame metadata as uml://types when resources are awkward
generate_uml_batchMultiple diagrams in one call (cap: MCP_BATCH_MAX_ITEMS)
ToolsThe Tools tool exposed by this server.
Vercel1. Connect the repo to [Vercel](https://vercel.com) 2. Use https://<project>.vercel.app/mcp 3. Keep /mcp in all MCP client URLs
Smithery1. Open [smithery.ai/new](https://smithery.ai/new), choose **URL** 2. Enter https://<project>.vercel.app/mcp 3. Configure display name, description, and homepage

Example prompts to try

  • Use Uml MCP to generate uml.
  • Use Uml MCP to validate uml.
  • Use Uml MCP to list diagram types.

Frequently asked questions

It connects Uml MCP to MCP-compatible AI assistants such as Claude and Cursor, exposing 7 tools (generate_uml, validate_uml, list_diagram_types, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Uml MCP directly.