cloudwright — Claude Code MCP server: what it does, how to install
Generates typed cloud architecture specs, cost estimates, compliance reports, and IaC for AWS, Azure, and GCP through natural language.
claude mcp add cloudwright -- uvx cloudwright-ai-mcpWhat cloudwright 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.
What it helps with
- 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 for the agent
- 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
How to install cloudwright
Platform CLI
claude mcp add cloudwright -- uvx cloudwright-ai-mcpuvx runs the command named after the package; if the README names another one, use uvx --from cloudwright-ai-mcp <command>
Platform CLI
codex mcp add cloudwright -- uvx cloudwright-ai-mcpuvx runs the command named after the package; if the README names another one, use uvx --from cloudwright-ai-mcp <command>
Config file
{
"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>
Config file
{
"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>
Platform CLI
gemini mcp add cloudwright uvx cloudwright-ai-mcpuvx runs the command named after the package; if the README names another one, use uvx --from cloudwright-ai-mcp <command>
Step by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more
Questions about cloudwright
How do I install cloudwright in Claude Code?
Run claude mcp add cloudwright -- uvx cloudwright-ai-mcp.
What does cloudwright do?
It translates system requirements into typed YAML specifications, IaC templates, cost breakdowns, and compliance reports mapped to industry standards.
Does cloudwright require an API key to function?
Generating new designs or running interactive chat requires ANTHROPIC_API_KEY or OPENAI_API_KEY. Reviewing compliance, evaluating migration evidence, and calculating costs run entirely offline.
