UML-MCP

UML-MCP Server is an MCP (Model Context Protocol) powered diagram generation service that turns natural-language prompts into professional diagrams.

CommunityOnlineNo sign-inGlobalFreeRead-only

What it can do

  • List Diagram Types: Find supported diagram types and their renderer/formats. Input optional query, backend, output_format, and limit filters; returns matching type metadata. Use this when you are unsu
  • Generate Uml Batch: Render several independent diagrams in one call using bounded concurrency. Input items use the same diagram_type/code/format/theme/scale fields as generate_uml; returns ordered per
  • Generate Uml: Render one UML or diagram from source code. Input diagram_type, code, optional output_format/theme/scale/output_dir; returns renderer metadata plus URL and inline image data when appropr

What data it sees

Do you need an account

No: the server works without sign-in

UML-MCP Server is an MCP (Model Context Protocol) powered diagram generation service that turns natural-language prompts into professional diagrams. It supports PlantUML, Mermaid, and Kroki-backed formats, so users can either describe what they want in plain language or provide diagram code directly. The server validates and renders many UML and architecture diagram types (class, sequence, activity, state, component, deployment, ERD, C4, and more), then returns shareable outputs such as SVG/PNG/PDF URLs (and file output when running locally). It is designed for seamless use with MCP clients like Cursor and Claude Desktop, with both local and remote deployment options.

How to connect

How to connect UML-MCP to Claude

The server address to paste into Claude settings:

https://uml-antoinebou12.run.tools

  1. Open Claude (claude.ai or the desktop app).
  2. Go to Settings → Connectors.
  3. Click Add custom connector.
  4. Paste the server address copied below into Remote MCP server URL and click Add.
  5. In a chat, click + → Connectors and switch the new connector on.

Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.

Authorization

After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.

How to connect UML-MCP to ChatGPT

The server address to paste into ChatGPT settings:

https://uml-antoinebou12.run.tools

  1. Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
  2. Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
  3. Open Settings → Connectors and click Create.
  4. Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
  5. Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
  6. In a new chat open + → Apps/Connectors and enable the connector.

OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.

Authorization

On first use ChatGPT opens the service's sign-in window. Sign in and approve access.

How to connect UML-MCP to Cursor

The server address to paste into Cursor settings:

https://uml-antoinebou12.run.tools

Fastest: click Open in Cursor below and confirm the prompt.

Manually:

  1. In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
  2. Paste the JSON copied below into ~/.cursor/mcp.json (per project: .cursor/mcp.json in the repo root).
  3. Save the file. The server appears in the MCP list; authorize it there if asked.

Authorization

If the service needs sign-in, an authorize button appears next to the server in the MCP list.

Server tool list (4)

Raw names from tools/list. Only developers need these.

list_diagram_typesFind supported diagram types and their renderer/formats. Input optional query, backend, output_format, and limit filters; returns matching type metadata. Use this when you are unsure which diagram type or format to choose.
generate_uml_batchRender several independent diagrams in one call using bounded concurrency. Input items use the same diagram_type/code/format/theme/scale fields as generate_uml; returns ordered per-index results and keeps partial failures isolated. Use this for multiple diagrams, not repeated repair attempts for one invalid diagram.
generate_umlRender one UML or diagram from source code. Input diagram_type, code, optional output_format/theme/scale/output_dir; returns renderer metadata plus URL and inline image data when appropriate. Use when you already have valid or nearly valid diagram source; call validate_uml first for uncertain complex syntax.
validate_umlValidate diagram type, format, size, and syntax locally without rendering. Input diagram_type/code/output_format and optional strict=true for additional Mermaid/D2 checks; returns structured diagnostics, suggestions, and deterministic normalization details. Use before rendering complex or uncertain source.