# cloudwright

Generates typed cloud architecture specs, cost estimates, compliance reports, and IaC for AWS, Azure, and GCP through natural language.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 33
- Author: xmpuspus
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/xmpuspus/cloudwright
- Updated: 2026-08-24
- HTML: https://affpapa.org/en/nevibecode/mcp/cloudwright

## What it does

The server provides agent tools to model cloud infrastructure across AWS, GCP, Azure, and Databricks. It takes natural language prompts and produces a typed YAML spec alongside deployable code for Terraform, OpenTofu, Pulumi, or CloudFormation. Exported templates enforce safe baselines automatically, enabling S3 bucket versioning and database disk encryption.

Built-in compliance checks map architectural components directly against HIPAA, SOC 2, PCI-DSS, and ISO 27001 control IDs before resources get created. The migration planning engine structures service dependencies into distinct phases and evaluates evidence gates. The engine focuses strictly on assessment and planning, leaving data replication and DNS switching untouched.

Running the server requires `uvx cloudwright-ai-mcp`. Spec validation and migration checks run offline, but generation tasks call an external model and require `ANTHROPIC_API_KEY` or `OPENAI_API_KEY`.

## Requirements
- Needs: Python and uv (commands run via uvx)

## Install

### Claude Code (native platform)

**Platform CLI**
```bash
claude mcp add cloudwright -- uvx cloudwright-ai-mcp
```
uvx runs the command named after the package; if the README names another one, use uvx --from cloudwright-ai-mcp <command>

### Codex

**Platform CLI**
```bash
codex mcp add cloudwright -- uvx cloudwright-ai-mcp
```
uvx runs the command named after the package; if the README names another one, use uvx --from cloudwright-ai-mcp <command>

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "cloudwright": {
            "command": "uvx",
            "args": [
                "cloudwright-ai-mcp"
            ]
        }
    }
}
```
uvx runs the command named after the package; if the README names another one, use uvx --from cloudwright-ai-mcp <command>

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "cloudwright": {
            "type": "stdio",
            "command": "uvx",
            "args": [
                "cloudwright-ai-mcp"
            ]
        }
    }
}
```
uvx runs the command named after the package; if the README names another one, use uvx --from cloudwright-ai-mcp <command>

### Gemini CLI

**Platform CLI**
```bash
gemini mcp add cloudwright uvx cloudwright-ai-mcp
```
uvx runs the command named after the package; if the README names another one, use uvx --from cloudwright-ai-mcp <command>

## When to use it
- export validated Terraform or Pulumi templates from a specification
- audit architecture against HIPAA, SOC 2, and FedRAMP control IDs
- calculate regional component costs before provisioning resources
- structure migration waves and evaluate readiness gates

## Example prompts
- Design an AWS architecture for a HIPAA-compliant API using cloudwright
- Evaluate spec.yaml against SOC 2 and FedRAMP security controls
- Generate Terraform files and estimate running costs for spec.yaml

## Similar
- [mcp-server](https://affpapa.org/en/nevibecode/mcp/mcp-server.md) — MCP server · ★ 43872
- [Coder](https://affpapa.org/en/nevibecode/mcp/coder.md) — MCP server · ★ 17160
- [firebase-mcp](https://affpapa.org/en/nevibecode/mcp/firebase-mcp.md) — MCP server · ★ 4481
- [Radar Kubernetes MCP Server](https://affpapa.org/en/nevibecode/mcp/radar-kubernetes-mcp-server.md) — MCP server · ★ 3905
- [Supabase](https://affpapa.org/en/nevibecode/mcp/supabase.md) — MCP server · ★ 2969
- [Microsoft Fabric MCP Server](https://affpapa.org/en/nevibecode/mcp/microsoft-fabric-mcp-server.md) — MCP server · ★ 3799

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md