Ilograph MCP Server
About
# Ilograph MCP Server A comprehensive Model Context Protocol (MCP) server for automated Ilograph diagram generation from codebases. This server analyzes source code across multiple programming languages and generates native .ilograph files that can be opened directly in the Ilograph editor, with optional rendering via…
Details
- License
- MIT license
Explore
- Native .ilograph File Generation: Creates .ilograph files that open directly in Ilograph editor
- Multi-Language Support: Analyze Python, JavaScript/TypeScript, and Java codebases
- MCP Protocol Compliance: Full integration with AI assistants (JetBrains AI Assistant, GitHub Copilot)
- Optional Export API Integration: Render diagrams as SVG, PNG, HTML, or PDF (requires API key)
- Multiple Perspectives: Generate diagrams from different architectural viewpoints
- Containerized Deployment: Docker support with multi-stage builds
- Production Ready: Comprehensive logging, monitoring, and error handling
- Extensible Architecture: Modular design for easy language and feature additions
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
Ilograph MCP ServerCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
pip install -e .
Copy the example environment file and configure your settings:
cp env.example .env
Key configuration options:
- ILOGRAPH_API_KEY: Your Ilograph API key for rendering diagrams (optional, only needed for SVG/PNG/PDF export)
- MCP_HOST: Server host (default: localhost)
- MCP_PORT: Server port (default: 8000)
- LOG_LEVEL: Logging level (DEBUG, INFO, WARNING, ERROR)
pip install -e ".[dev]"
pre-commit install
The server exposes the following MCP tools:
1. analyze_codebase: Extract architectural information from source code
2. generate_diagram: Create Ilograph diagrams from analysis results
3. render_diagram: Render diagrams using Ilograph Export API
4. save_diagram: Save diagrams to files
5. get_supported_languages: List supported programming languages
6. health_check: Check server health status
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"ilograph mcp server": {
"ilograph-mcp-server": {
"command": "docker",
"args": [
"build",
"-t",
"ilograph-mcp-server",
"."
]
}
}
}
}McpServers
{
"ilograph-mcp-server": {
"command": "docker",
"args": [
"build",
"-t",
"ilograph-mcp-server",
"."
]
}
}A comprehensive Model Context Protocol (MCP) server for automated Ilograph diagram generation from codebases. This server analyzes source code across multiple programming languages and generates native .ilograph files that can be opened directly in the Ilograph editor, with optional rendering via the Ilograph Export API.
🚀 Features
- Native .ilograph File Generation: Creates .ilograph files that open directly in Ilograph editor
- Multi-Language Support: Analyze Python, JavaScript/TypeScript, and Java codebases
- MCP Protocol Compliance: Full integration with AI assistants (JetBrains AI Assistant, GitHub Copilot)
- Optional Export API Integration: Render diagrams as SVG, PNG, HTML, or PDF (requires API key)
- Multiple Perspectives: Generate diagrams from different architectural viewpoints
- Containerized Deployment: Docker support with multi-stage builds
- Production Ready: Comprehensive logging, monitoring, and error handling
- Extensible Architecture: Modular design for easy language and feature additions
📋 Requirements
- Python 3.10 or higher
- Docker (optional, for containerized deployment)
- Ilograph API key (for diagram rendering)
🛠️ Installation
Using pip
```bash
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
