UML-MCP
Supports generating Excalidraw diagrams as one of the specialized diagram types available through the server.
Enables generating Mermaid diagrams from textual definitions and rendering them to SVG, PNG, PDF, JPEG, or base64 outputs.
Allows generating UML diagrams, including class, sequence, activity, use case, state, component, deployment, and object diagrams.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@UML-MCP Generate a UML class diagram for a library management system"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
UML-MCP: Diagram Generation via MCP
Generate UML and other diagrams through the Model Context Protocol.
At a glance
Topic | What you get |
Diagrams | 30+ types: UML (Class, Sequence, Activity, Use Case, State, Component, Deployment, Object), Mermaid, D2, Graphviz, TikZ, ERD, BlockDiag, BPMN, C4, and more via Kroki |
MCP tools |
|
Outputs | SVG, PNG, PDF, JPEG, base64 (availability varies by diagram type) |
Pipeline | Kroki first, then PlantUML or Mermaid.ink |
Deployment |
Source | URL |
Live MCP (HTTP) | |
Smithery catalog |
Quick Start
Choose your mode
Remote (recommended): Fast setup over HTTP MCP with Vercel serverless runtime
Local: stdio process for file output and local debugging
Remote quick start (Vercel HTTP MCP)
Configuration for the public Vercel deployment:
"uml-mcp": {
"transport": "http",
"url": "https://uml-mcp.vercel.app/mcp"
}Local quick start (stdio MCP)
git clone https://github.com/antoinebou12/uml-mcp.git && cd uml-mcp
uv sync
uv run python server.pyExample client configs:
config/cursor_config.jsonconfig/claude_desktop_config.jsonconfig/README.mdfor exact config file locationsClaude Code: install the bundled plugin from the repo marketplace (see below) or read docs/integrations/claude_code.md
Claude Code plugin
Adds the hosted HTTP MCP server plus a diagram skill (no settings.json paste). In Claude Code:
/plugin marketplace add https://github.com/antoinebou12/uml-mcp
/plugin install uml-mcp@uml-mcp-pluginsUse a local path instead of the GitHub URL if you already cloned this repo. Custom endpoints and validation: docs/integrations/claude_code.md.
Related MCP server: Draw.io MCP Server
Remote vs Local
Transport: Remote uses HTTP MCP, local uses stdio by default
Runtime: Remote runs on Vercel, local runs in your Python environment
File writes: Remote is read-only (no
output_dir), local supportsoutput_dirReturned data: Both return URL + base64; local can also save files
Environment variables: Remote is managed server-side; local reads your env config
MCP clients must call /mcp, not the site root.
Supported Diagram Types
Category | Examples |
UML (PlantUML) | Class, Sequence, Activity, Use Case, State, Component, Deployment, Object |
General | Mermaid, D2, Graphviz, ERD, BlockDiag, BPMN, C4 |
Specialized | TikZ, Excalidraw, Nomnoml, Pikchr, Structurizr, SVGBob, WaveDrom, WireViz, … |
Full list with supported formats: run python server.py --list-tools or query uml://types and uml://formats.
MCP Tools and Resources
Tools
Tool | Purpose |
| Render a diagram; omit |
| Structural validation before render; |
| Same metadata as |
| Multiple diagrams in one call (cap: |
Resources (uml://)
Resource | Description |
| Diagram types, backends, supported formats per type |
| Starter templates per type; see BPMN 2.0.2 guide for element and flow reference (docs) |
| Example diagrams per type; Mermaid documents named samples (sequence API, Gantt) alongside |
| Output formats per type |
| Type → backend → formats matrix used for validation |
| Server name, version, tools, prompts, Kroki/PlantUML URLs |
| Recommended plan-then-generate workflow |
Deployment
Vercel
This repo includes vercel.json for serverless deployment.
Connect the repo to Vercel
Use
https://<project>.vercel.app/mcpKeep
/mcpin all MCP client URLs
Smithery
Open smithery.ai/new, choose URL
Enter
https://<project>.vercel.app/mcpConfigure display name, description, and homepage
Detailed guide: docs/integrations/vercel_smithery.md
Docker
Default image serves FastAPI on port 8000 with MCP HTTP at http://127.0.0.1:8000/mcp.
# Full local stack (local Kroki + mermaid + blockdiag)
docker compose up -d
# API + MCP only (public Kroki)
docker build -t uml-mcp . && docker run -p 8000:8000 uml-mcp
# stdio MCP subprocess mode
docker run -i uml-mcp python server.py --transport stdioConfiguration (Local runtime)
These variables apply to local/self-hosted runs. Remote Vercel endpoint settings are managed server-side.
Variable | Description | Default |
| Kroki server URL |
|
| PlantUML server URL |
|
| Diagram output directory |
|
| Disable file writes |
|
| Max diagram code length |
|
| Max items per |
|
| HTTP rate limit per IP for diagram/MCP routes ( |
|
| Use local Kroki instance |
|
| Use local PlantUML instance |
|
Full options: docs/configuration.md
Architecture
Typical flow when a user asks an MCP-enabled assistant for a diagram: the assistant calls generate_uml, the server renders via Kroki, then returns URLs and optional base64 to the assistant for the user.
server.py -- MCP entry point (stdio/HTTP)
app.py -- FastAPI REST API + MCP HTTP at /mcp
api/app.py -- legacy re-export of root app (Vercel FastAPI preset uses root app.py)
mcp_core/
core/ -- config, server, CLI, utilities, diagram pipeline
tools/ -- generate_uml, validate_uml
prompts/ -- diagram generation prompts
resources/ -- uml:// resource handlers
tools/kroki/ -- Kroki, PlantUML, Mermaid, D2 clientsDevelopment
# Install dev dependencies
uv sync --all-groups
# Run tests
uv run pytest tests/ -v
# Lint
uv run ruff check . && uv run ruff format --check .
# Local CI
make ciDocumentation
Online: antoinebou12.github.io/uml-mcp
Local:
uv run mkdocs servethen open http://127.0.0.1:8000
Contributing
License
Acknowledgements
PlantUML | Kroki | Mermaid | D2
Star History
Available Tools
4 toolsgenerate_umlBIdempotent
Generate any UML or diagram by type (class, sequence, mermaid, d2, etc.)
Inputs: code (required), diagram_type (required), scale, theme, +2 more. Returns: object
generate_uml_batchAIdempotent
Generate multiple diagrams in one call. Each item is like generate_uml (diagram_type, code, output_format?, theme?, scale?). Optional shared output_dir for all items. Returns a list of per-index results or errors.
Inputs: items (required), output_dir. Returns: object
list_diagram_typesARead-onlyIdempotent
List supported diagram types with Kroki backend, description, and formats (same data as uml://types resource). Use when the client cannot read resources.
Inputs: no named parameters. Returns: object
validate_umlARead-onlyIdempotent
Validate diagram type, format, code length, and basic syntax locally before render (no Kroki call). Returns errors and suggestions.
Inputs: code (required), diagram_type (required), strict, output_format. Returns: object
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 4 tools
Each tool has a clearly distinct role: listing available types, validating before render, generating a single diagram, and batch-generating multiple diagrams. The single vs. batch generation pair is unambiguous given the explicit descriptions.
All four tools follow a consistent verb_noun snake_case pattern (list_diagram_types, generate_uml, generate_uml_batch, validate_uml). No mixing of conventions.
Four tools is well-scoped for a diagram rendering service, covering discovery, validation, single generation, and batch generation without redundancy. Each tool clearly earns its place.
The surface covers the full diagram workflow: discover types, validate, generate, and batch generate. Minor gap in that there is no explicit info/help tool, though list_diagram_types largely covers discovery.
Maintenance
Related MCP Connectors
Create workflow, sequence, architecture, and mind map diagrams via AI assistants.
Turn calls and notes into process flow diagrams in Claude, ChatGPT, VS Code, Cursor, and Teams.
Generate dynamic Mermaid diagrams and charts with AI assistance. Customize styles and export diagr…
Render, validate, encode/decode PlantUML diagram-as-code; 22 diagram types. Free, no auth.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables AI assistants to generate UML diagrams from text descriptions using PlantUML, supporting multiple output formats (PNG, SVG, PDF), syntax validation, and diagram source extraction.10 npmMIT
- AlicenseBqualityAmaintenanceEnables AI agents to programmatically create, modify, and analyze Draw.io diagrams through the Model Context Protocol. Supports generating architectural diagrams, flowcharts, and visualizations with bidirectional communication between AI systems and Draw.io.13120 npm1,498MIT
- AlicenseNot gradedqualityFmaintenanceEnables AI-driven graphical diagram creation and manipulation using natural language, with support for BPMN workflows, analysis, and manual editing via the Model Context Protocol.1MIT
- AlicenseAqualityBmaintenanceGenerates UML and other diagrams (30+ types) via the Model Context Protocol, supporting multiple output formats and deployment options.7109MIT