kompas-3d-ai-bridge
MCP server that connects AI agents to KOMPAS-3D CAD, enabling automated 3D document operations through deterministic COM/API7 calls.
README
KOMPAS-3D AI Bridge
AI engineering bridge for KOMPAS-3D using Python, COM/API7 and MCP.
The project connects AI agents and coding assistants to KOMPAS-3D through a deterministic execution layer.
Architecture
AI / LLM / Coding Agent | v MCP | v Python deterministic bridge | v KOMPAS COM / API7 | v KOMPAS-3D
Features
- AI agent integration with KOMPAS-3D
- MCP server
- Python deterministic execution layer
- KOMPAS COM / API7 integration
- Parts and assemblies
- 3D document automation
- Engineering-oriented CAD operations
- Validation before and after execution
- Separation between probabilistic AI reasoning and deterministic CAD API calls
Requirements
- Windows
- KOMPAS-3D
- Python 3
- pywin32
Install dependencies:
pip install -r requirements.txt
Project structure
bootstrap/ Bridge startup scripts
common/ Shared components
config/ Example configuration
jobs/ Job definitions
mcp/ MCP server
skills/ Agent skills
src/ Bridge implementation
tests/ Tests and self-checks
Configuration
Copy:
config/agent_config.example.json
to:
config/agent_config.json
Then adjust paths for your local environment.
The real agent_config.json is excluded from Git.
Safety
Customer CAD data and project-specific files are not included in this repository.
The repository excludes local CAD files, runtime logs, workspaces, local configuration and secrets.
Version
Current public base: 1.1.14_CAP2
Disclaimer
This is an independent engineering automation project.
KOMPAS-3D is a product of ASCON. This project is not an official ASCON product and is not affiliated with or endorsed by ASCON.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.