What AI providers are supported?
Supported providers include Claude 4/3 (Opus & Sonnet), GPT-4o/4, Google Gemini Pro/Flash, OpenRouter (100+ models), DeepSeek (reasoning models), and local models via Ollama.
@Louranicas
Basic information
Claude-Optimized Deployment Engine (CODE) - AI-powered infrastructure automation platform with Rust-accelerated Circle of Experts system. Features 20x performance boost, 11 MCP servers, 51+ tools, and comprehensive security hardening. 85-90% complete.
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"claude-optimized-deployment": {
"command": "python",
"args": [
"-m",
"venv",
"venv"
]
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Claude-Optimized Deployment Engine (CODE) is a production-ready AI-powered infrastructure automation platform with comprehensive MCP (Model Context Protocol) integration and Rust-accelerated performance. It provides multi-AI consultation via the Circle of Experts system and automates deployment pipelines across Docker, Kubernetes, Azure, and other cloud services through 11 MCP servers with 51+ tools. It is designed for DevOps engineers and teams seeking automated, AI-driven deployment and operations.
Clone the repository, run make dev-setup or manually set up a Python virtual environment, install requirements, and optionally build Rust performance modules with make rust-build. Configure at least one AI provider API key (e.g., ANTHROPIC_API_KEY) and optional MCP server credentials (e.g., AWS_ACCESS_KEY_ID, SLACK_BOT_TOKEN). Use the provided Python examples or integrate the SDK into your own scripts to invoke Circle of Experts consultations and MCP deployment automation.
Supported providers include Claude 4/3 (Opus & Sonnet), GPT-4o/4, Google Gemini Pro/Flash, OpenRouter (100+ models), DeepSeek (reasoning models), and local models via Ollama.
Python 3.10+, at least one AI API key (Anthropic, OpenAI, Google, etc.), and Docker (for container automation). The Rust toolchain is optional but recommended for performance modules. Kubernetes cluster and cloud provider credentials are optional for full infrastructure automation.
Set environment variables for the required MCP servers: e.g., `AWS_ACCESS_KEY_ID` for S3, `SLACK_BOT_TOKEN` for Slack notifications, and `AZURE_DEVOPS_TOKEN` for Azure DevOps integration.
Yes. The project reports 95%+ completion with production deployments verified. It has passed 9 security audits and includes real-time monitoring, alerting, and team integration. Minor features like advanced GitOps and canary deployments are planned for v1.1.
No, Rust is optional. The core Python functionality works without it, but building the Rust performance modules (`make rust-build`) provides 2–20x speed improvements for consensus, aggregation, and pattern analysis.
An MCP server for Azure DevOps

Your AI can finally reach the physical world. Kilo is an AI-first IoT platform for commercial and industrial operations, and this connector hands a live deployment to the AI client you already use. Not an export. Not a
Open source MCP Servers for AWS
MCP server connecting to Kubernetes
Official OutageDeck MCP server for vendor-published cloud and SaaS status, incident timelines, and observed uptime history.
Comments