structurizr-dsl-debug-mcp
Mcp server to connect to structurizer dsl rendered in the browser and return error messages regarding parsing to Cursor IDE
Documentation
Structurizr DSL Debugger for Cursor
A specialized tool for debugging Structurizr DSL syntax issues in Cursor IDE. This tool integrates with Cursor using the Model Context Protocol (MCP) to provide real-time Structurizr DSL error detection, analysis, and fix suggestions.
Features
- ๐ Real-time error detection - Automatically captures syntax errors from Structurizr DSL files
- ๐ ๏ธ Suggested fixes - Provides intelligent suggestions to correct common DSL errors
- ๐ Browser integration - Connects to Chrome with Structurizr pages to monitor errors
- ๐งฉ Cursor IDE integration - Seamlessly integrates with Cursor using MCP tools
- โ๏ธ Configurable - Support for custom Structurizr port configuration
- ๐ Error history - Maintains logs of captured errors for review
Requirements
- Node.js 14+
- Cursor IDE
- Google Chrome with remote debugging enabled
- Structurizr Lite running locally (typically on port 8080)
Installation
1. Clone this repository:
git clone https://github.com/your-username/structurizr-dsl-debugger.git
cd structurizr-dsl-debugger2. Install dependencies:
npm install3. Set up Cursor IDE integration:
npm run setupUsage
Starting Structurizr
1. Run Structurizr Lite (if not already running):
docker run -it --rm -p 8080:8080 -v /path/to/workspace:/workspace structurizr/liteUsing the Debugger
1. Launch Chrome with remote debugging enabled:
google-chrome --remote-debugging-port=9222 http://localhost:80802. Start the DSL debugger:
# Standard start (default port 8080)
npm start
# With custom Structurizr port
STRUCTURIZR_PORT=9090 npm start
# Using the launcher with interactive prompts
npm run debug3. In Cursor IDE, use the MCP tools:
connectToBrowser: { "debugPort": 9222, "structurizrPort": 8080 }
getDslErrors: { "count": 5 }
clearDslErrors: {}
fixDslError: { "line": 776, "fix": "dynamic ContainerName ErrorHandlingFlow {" }Simplified Version
If you encounter issues with the main debugger, try the simplified version:
node simplified-dsl-debugger.jsWith shorter MCP tool names:
connect: { "port": 9222 }
errors: { "count": 5 }
fix: { "line": 776, "solution": "dynamic ContainerName ErrorHandlingFlow {" }Utility Scripts
- Capture errors directly:
npm run capture- View captured errors:
npm run errorsTroubleshooting
Chrome Connection Issues
- Ensure Chrome is running with remote debugging enabled on port 9222
- Check if Chrome is already running with the `--remote-debugging-port` flag
- Try restarting Chrome with: `google-chrome --remote-debugging-port=9222 http://localhost:8080`
MCP Tool Issues
- Verify the MCP server is running: `npm start`
- Try using the simplified version: `node simplified-dsl-debugger.js`
- Check the logs directory for captured errors
- Restart Cursor IDE
Port Conflicts
- Structurizr default port is 8080
- If another application is using port 8080, you can:
- Change the Structurizr port
- Update the debugger to use the new port: `STRUCTURIZR_PORT=9090 npm start`
License
MIT
Frequently asked questions
What is structurizr-dsl-debug-mcp?
structurizr-dsl-debug-mcp is Mcp server to connect to structurizer dsl rendered in the browser and return error messages regarding parsing to Cursor IDE
How do I install structurizr-dsl-debug-mcp?
Open the GitHub repository and follow its README. Most MCP servers are added to your client's MCP config, then called by your agent.
Is structurizr-dsl-debug-mcp open source?
Yes โ it is hosted on GitHub at https://github.com/ViperJuice/Structurizr-DSL-Debug-MCP and has 2 stars.
Related MCP tools
An MCP server that installs other MCP servers for you JavaScript-based implementation. Trusted by 1400+ developers. Trusted by 1400+ developers.
MCP server for interacting with the iOS simulator JavaScript-based implementation. Trusted by 1200+ developers. Trusted by 1200+ developers.
A Model Context Protocol server that provides read-only access to MySQL databases. This server enables LLMs to inspect database schemas and execute read-only...
This is an MCP server that allows you to directly download transcripts of YouTube videos. JavaScript-based implementation.
The all-in-one Desktop & Docker AI application with built-in RAG, AI agents, No-code agent builder, MCP compatibility, and more.
An AI-powered task-management system you can drop into Cursor, Lovable, Windsurf, Roo, and others. Built for the Model Context Protocol to enhance AI capabiliti
Run your own MCP server? See who uses it and what to fix.
Measure it with TrackMCP