About PlantUML-MCP-Server
PlantUML-MCP-Server provides PlantUML diagram generation capabilities for Claude Desktop and Claude Code. The repository has moved to the Infobip organization; the npm package remains published under the same name.
Key features
- 01Generate PlantUML diagrams
- 02Use with Claude Desktop
- 03Use with Claude Code
- 04Install through the published npm package
Use cases
- 01Generate diagrams from a Claude Desktop workflow
- 02Create PlantUML diagrams in Claude Code
- 03Continue using the existing npm package
MCP support
The project is an MCP server that provides PlantUML diagram generation to MCP-compatible clients such as Claude Desktop and Claude Code.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
Tools
3Saved tool list · updated 2w ago
| Parameter | Type | Required | Description |
|---|---|---|---|
| plantuml_code | string | Yes | PlantUML diagram code. Will be automatically validated for syntax errors before generating the diagram URL. |
| format | enum | No | Output image format (SVG or PNG)svg | png |
| output_path | string | No | Optional. Path to save diagram locally. Automatically creates all necessary parent directories. Restricted to current working directory by default. Set PLANTUML_ALLOWED_DIRS env var (colon-separated paths, or "*" for unrestricted) to allow additional directories. Only .svg and .png extensions permitted. |
Details
From the project README🚚 Repository Moved
This repository has been moved to the Infobip organization:
➡️ https://github.com/infobip/plantuml-mcp-server
What Changed
- Source code: Now maintained under Infobip organization
- Issues/PRs: Please create new ones in the Infobip repo
- NPM package: Still published as
plantuml-mcp-server(no changes needed)
For Users
No action required - the npm package plantuml-mcp-server continues to work exactly the same.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.