# Infoundry

> AI-powered cloud architect agent that analyzes codebases and generates optimized infrastructure as code.

- **Type:** MCP server
- **Install:** `agentstack add mcp-crypticsaiyan-infoundry`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [crypticsaiyan](https://agentstack.voostack.com/s/crypticsaiyan)
- **Installs:** 0
- **Category:** [Cloud & Infrastructure](https://agentstack.voostack.com/c/cloud-infrastructure)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [crypticsaiyan](https://github.com/crypticsaiyan)
- **Source:** https://github.com/crypticsaiyan/infoundry

## Install

```sh
agentstack add mcp-crypticsaiyan-infoundry
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# InFoundry

InFoundry is a self-adaptive Cloud Architect + SRE agent that inspects codebases and telemetry, proposes deployable IaC/CI changes, runs safe test deployments, and iteratively optimizes cost, latency, and reliability with human-in-the-loop approvals.

Demo: https://youtu.be/FSsgkSt77LM

## Features

- **AI-Powered Architecture Recommendations** - Uses fine-tuned Oumi model for intelligent cloud architecture decisions
- **Kestra Pipeline Orchestration** - End-to-end workflow from repo analysis to PR creation
- **MCP Server for Cline Integration** - Expose all tools via Model Context Protocol
- **React UI Dashboard** - Visual architecture editor with React Flow
- **IaC Generation** - Automatic Terraform generation for AWS

## Quick Start

### Prerequisites
- Python 3.11+
- Node.js 18+
- Optional: Docker, kind, localstack

### Installation

```bash
# Clone the repository
git clone https://github.com/your-org/infoundry.git
cd infoundry

# Install Python dependencies
pip install -r requirements.txt

# Install UI dependencies
cd ui && npm install && cd ..

# Install MCP server dependencies
cd infoundry-mcp-server && npm install && npm run build && cd ..
```

### Run the UI
```bash
cd ui
cp .env.example .env.local
# Edit .env.local with your Kestra credentials if needed
npm run dev
# Open http://localhost:3000
```

### Run the Oumi Server
```bash
cd oumi
python serve.py
# API available at http://localhost:8000
```

## Project Structure

```
infoundry/
├── docs/                    # Documentation
├── examples/                # Sample data files
├── infoundry-mcp-server/    # Cline MCP integration
├── orchestrator/            # Kestra pipeline definitions
├── oumi/                    # AI model training & serving
├── scripts/                 # Utility scripts
├── tests/                   # Unit tests
└── ui/                      # Next.js React dashboard
```

## Documentation

- [Blueprint & Architecture](docs/BLUEPRINT.md) - Full system design
- [Kestra Architecture](docs/kestra-architecture.md) - Pipeline documentation
- [Oumi Model](oumi/README.md) - AI model training guide
- [MCP Server](infoundry-mcp-server/README.md) - Cline integration

## Testing

```bash
# Python tests
pip install pytest fastapi httpx
pytest tests/ -v

# MCP server tests
node tests/test_mcp_server.mjs
```

## Screenshots

| Screenshot | Description |
|------------|-------------|
|  | Cline MCP Integration |
|  | Kestra Pipeline Flows |
|  | Open Source Architecture |
|  | Application Screenshot |
|  | Application Screenshot |
|  | Application Screenshot |
|  | Application Screenshot |

## License

Released under the [MIT License](LICENSE).

## Source & license

This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [crypticsaiyan](https://github.com/crypticsaiyan)
- **Source:** [crypticsaiyan/infoundry](https://github.com/crypticsaiyan/infoundry)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** yes
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** yes
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/mcp-crypticsaiyan-infoundry
- Seller: https://agentstack.voostack.com/s/crypticsaiyan
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.