All servers / Design / PlantUML MCP server
PlantUML MCP server
Pure Node/JS Model Context Protocol (MCP) server for PlantUML, powered by the TeaVM-compiled engine. No Java runtime required.
Tested by ConnectATDScore 90 out of 100. Tested 2026-11-18 on package version 0.2.4. Package: @plantuml/mcp-js · source
Score breakdown
| Runs | 18 / 20 | |
|---|---|---|
| Tool descriptions | 20 / 20 | |
| Package safety | 20 / 20 | |
| Maintenance | 20 / 20 | |
| Adoption | 12 / 20 |
What we saw
- Starts and answers the MCP handshake: yes (3.9 seconds including download)
- Tools offered: 4
- Last published: 2026-11-11
- Weekly downloads (npm): 3,659
- License: MIT · Direct dependencies: 3
Want this server set up for your team?
ConnectATD builds AI automation and wires up MCP servers like this one. Tell us what you are trying to do.
Talk to ConnectATDTools and how they are described
Agents choose tools from these descriptions. Under each name you can see how many of its parameters are explained.
plantuml_versionno parametersReturns the version of the embedded PlantUML library (TeaVM JS build).
check_syntax1 of 1 parameter describedChecks the syntax of a single PlantUML diagram without rendering it. Returns a JSON object containing: 'valid' (boolean), 'diagramType' (if valid), 'lineCount', 'warnings' (list of non-fatal warnings), and on failure 'errorLineNumber' (1-based line number), 'errorMessage', 'errorLine' (the offending source line, when available), and 'errorContext'.
render_diagram1 of 1 parameter describedRenders a single PlantUML diagram to a deterministic SVG. Returns a JSON object containing: 'valid' (boolean), and when valid 'diagramType', 'lineCount', 'warnings' (list of non-fatal warnings) and 'svg' (the rendered SVG as a string). On failure it has the same error shape as check_syntax: 'errorLineNumber' (1-based), 'errorMessage', 'errorLine' (the offending source line, when available) and 'errorContext'.
explain_diagram1 of 1 parameter describedExplains how a single PlantUML diagram is parsed, line by line. Returns a JSON array of objects, each containing: 'input' (the source line(s) that produced the explanation), 'explain' (a human-readable explanation), and 'line' (1-based line number, when available).
Tested in a sandbox with an empty environment: no API keys, a throwaway folder, nothing from a real account. A passing test shows the server runs and responds. It is not a security audit.