Diseña arquitecturas en la nube, planifica migraciones y genera código de infraestructura compatible con análisis de costos y mapeo de cumplimiento automatizado.
También conocido como xmpuspus/cloudwright, cloudwright-ai-mcp
- Stars
- 33
- Herramientas
- —
- Descargas, 30 días
- 274
- Última versión
- 1.10.0
- Último commit
- 24 ago 2026
- Licencia
- MIT
¿Qué es Cloudwright MCP?
Cloudwright es un MCP server. Diseña arquitecturas en la nube, planifica migraciones y genera código de infraestructura compatible con análisis de costos y mapeo de cumplimiento automatizado.
Resumen generado a partir del README del proyecto
Acerca del MCP server de Cloudwright
Cloudwright permite a ingenieros DevOps y arquitectos diseñar arquitecturas en la nube y planificar migraciones complejas. Al proporcionar una interfaz única para AWS, GCP, Azure y Databricks, transforma descripciones en lenguaje natural en especificaciones tipadas, desgloses de costos y código de infraestructura. Los usuarios pueden generar Terraform, OpenTofu, Pulumi o CloudFormation a partir de un solo prompt de diseño.
Este MCP server se integra con varios agentes de codificación como Claude Code, Cursor y Windsurf para incorporar validaciones arquitectónicas directamente en el flujo de desarrollo. Mientras que comandos como design, modify, chat y adr requieren una API key de Anthropic u OpenAI para llamar a un modelo, la mayoría de las otras funciones, como la estimación de costos, el mapeo de cumplimiento y la planificación de migraciones, se ejecutan completamente offline. Esto permite una validación local rápida de los diseños de infraestructura frente a frameworks como HIPAA, SOC 2 y PCI-DSS sin depender constantemente de la red.
Qué puedes hacer con él
- 1Generar código de infraestructura compatibleConvierte una descripción textual de una configuración en la nube en una especificación completa de Terraform con valores de seguridad predeterminados integrados.
- 2Mapear la arquitectura con controles regulatoriosVerifica que un diseño de nube propuesto cumpla con estándares específicos de la industria como HIPAA o FedRAMP antes del despliegue.
- 3Planificar y verificar migraciones a la nubeOrganiza una migración en oleadas ordenadas y utiliza puertas de evidencia para asegurar que se cumplan todos los prerrequisitos.
- 4Estimar costos de recursos en la nubeObtén un desglose de costos sensible a la región para cada componente de una arquitectura propuesta.
Escrito a partir del README del proyecto. Cada caso de uso se verifica con una cita del mismo.
Cómo instalar Cloudwright MCP
Formatos verificados el 10 nov 2026Añadir a CursorAñadir a GooseInstalar Cloudwright MCP en Claude Code
$ claude mcp add cloudwright -- uvx cloudwright-ai-mcpInstalar Cloudwright MCP en Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"cloudwright": {
"command": "uvx",
"args": [
"cloudwright-ai-mcp"
]
}
}
}Instalar Cloudwright MCP en VS Code
.vscode/mcp.json
{
"servers": {
"cloudwright": {
"type": "stdio",
"command": "uvx",
"args": [
"cloudwright-ai-mcp"
]
}
}
}Instalar Cloudwright MCP en VS Code CLI
$ code --add-mcp '{"name":"cloudwright","type":"stdio","command":"uvx","args":["cloudwright-ai-mcp"]}'Instalar Cloudwright MCP en Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"cloudwright": {
"command": "uvx",
"args": [
"cloudwright-ai-mcp"
]
}
}
}Instalar Cloudwright MCP en Codex
$ codex mcp add cloudwright -- uvx cloudwright-ai-mcpInstalar Cloudwright MCP en Codex config.toml
~/.codex/config.toml
[mcp_servers.cloudwright] command = "uvx" args = ["cloudwright-ai-mcp"]
Instalar Cloudwright MCP en Gemini CLI
$ gemini mcp add -s user cloudwright uvx -- cloudwright-ai-mcpInstalar Cloudwright MCP en Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"cloudwright": {
"command": "uvx",
"args": [
"cloudwright-ai-mcp"
]
}
}
}Configuración
ANTHROPIC_API_KEY
| Nombre | Descripción | Tipo |
|---|---|---|
| ANTHROPIC_API_KEY | — |
Verificaciones automáticas
Ejecutado 13 nov 2026Informe completo →Pasó nuestras verificaciones automáticas. Esto no es una auditoría de seguridad: lee el código y dale al servidor el acceso más limitado que necesite. Cómo funcionan las verificaciones
- Repositorio de origen vinculado y accesibleAprobado
- Licencia de código abierto (OSI)Aprobado
- Commit o lanzamiento en el último añoAprobado
- El nombre del paquete no es similar a un paquete popularAprobado
- El endpoint remoto usa HTTPSNo verificado
- Las herramientas destructivas están etiquetadasNo verificado
- Sin instrucciones ocultas para el modeloAprobado
- No hay avisos críticos en el paquete ni en sus dependenciasAprobado
README
Ver en GitHubCloudwright
Design a cloud architecture or plan a migration. Get costs, controls, code, and checked evidence.
pip install 'cloudwright-ai[cli]'
export ANTHROPIC_API_KEY=sk-ant-...
cloudwright design "HIPAA healthcare API on AWS with Postgres and Redis"
Cloudwright turns one line of English into a typed spec, a cost breakdown, a control-mapped compliance report,
and infrastructure code. A source estate and target become ordered migration waves, explicit costs,
and evidence gates. It covers AWS, GCP, Azure and Databricks across 114 service keys. Only design, modify,
chat and adr call a model. Every other command runs offline and needs no API key.
Quickstart · Migrations · Compliance · Agents · Docs · Changelog
A prompt produces a spec, a cost, a control-mapped report, and Terraform
- Spec. Typed YAML you commit, diff and review. Everything below reads from it.
- Cost. Per component and region-aware, with a confidence flag on every line.
- Compliance. HIPAA, SOC 2, PCI-DSS, FedRAMP, GDPR, ISO 27001 and NIST 800-53 control IDs.
- Infrastructure code. Terraform, OpenTofu, Pulumi (TypeScript or Python) and CloudFormation.
- Diagrams. ASCII, Mermaid, D2, and a web canvas you can edit by hand.
- An MCP server, so any coding agent runs the same checks inside its own loop.
Exports carry safe defaults. S3 gets a public-access block, SSE and versioning. RDS gets encryption, multi-AZ and deletion protection. EC2 gets IMDSv2. A compliance framework overrides the workload profile, and always forces encryption and high availability.
Quickstart
cloudwright design "HIPAA healthcare API on AWS with Postgres and Redis"
cloudwright cost spec.yaml --workload-profile medium
cloudwright compliance spec.yaml --frameworks hipaa,soc2
cloudwright export spec.yaml --format terraform -o ./infra
cloudwright plan spec.yaml --target terraform # proves it deploys, never applies
cloudwright migrate demo # packaged migration proof, fully offline
cloudwright chat --web # canvas at http://localhost:8765
Add --json before any subcommand for machine-readable output, or --stream to watch tokens arrive. Set ANTHROPIC_API_KEY or OPENAI_API_KEY for the four commands that need a model.
Migration plans stop when evidence is missing
The migration model covers infrastructure, applications, data, platforms, networks, facilities, and business services in one dependency graph. It works for on-premises, cloud, cross-cloud, hybrid, data-center, and application moves. It plans and checks work. It never copies data, applies infrastructure, switches traffic, or runs a cutover.
cloudwright migrate plan examples/migrations/ph-telco-project.yaml -o assessment.yaml
cloudwright migrate verify examples/migrations/ph-telco-project.yaml examples/migrations/ph-telco-evidence.yaml
The core has no telco fields. The first proof project selects an external ph_telco pack for subscriber,
billing, usage-record, number-porting, privacy, recovery, and source-shutdown gates. A manufacturing ERP
fixture proves the same planner works without that pack. Missing blocking evidence changes the result to
closed: false and makes migrate verify exit with code 2. Each evidence file carries the deterministic
assessment ID, so observations from an older target or cutover plan cannot close a revised assessment.
MCP clients use the same engine through plan_migration and verify_migration in the migration tool group.
See Migration planning and evidence for the file contract, Python API, HTTP routes, domain-pack format, limits, and recording commands.
Every finding carries the control ID it violates
Other tools scan infrastructure after you deploy it. Cloudwright maps each finding to its control before any
resource exists. The fix then costs a spec edit instead of a change ticket. HIPAA 164.312(a)(2)(iv), SOC 2 CC6.1
and FedRAMP SC-28 come from the built-in scanner, with no extra tooling. Checkov folds into the same report
when it sits on your PATH.
--oscalwrites an OSCAL 1.1.2 component-definition with deterministic UUIDs.--traceabilityprints the chain from component to resource to control to status.cloudwright planrunsterraform validateagainst the export, and never applies.
The review needs no API key and no network
cloudwright review runs the scorer, the linter and the validator over a spec, and returns one severity-ranked
report. The same three critics run inside cloudwright design. When blocking findings survive generation, the
architect repairs the spec once and records the change in spec.metadata.critique. Pass
Architect(repair=False) to turn that off.
Canvas edits never call the model, so they are instant and free
Add, drag, connect, edit and delete are deterministic frontend mutations. The Catalog drawer serves the resource
list per provider and five approved multi-resource modules. Its standards check flags orphan connections,
partial modules and missing tags. An intact module exports as a single Terraform module block, with the
catalog's pinned source and version.
One MCP server reaches 11 coding agents
cloudwright integrate --harness claude-code # exact wiring, in that client's format
cloudwright integrate --harness cursor --write # merge it into the right file
cloudwright integrate --rules --agent-file claude # a gate block for CLAUDE.md
Do not hand-write the config. cloudwright integrate emits it for Claude Code, Cursor, Cline, Windsurf, GitHub
Copilot, Zed, Codex CLI, Junie, Kiro and Antigravity. Aider gets a CLI-pipe recipe instead, because it speaks
no MCP. Every client wants a different shape: Zed wants context_servers, Copilot wants servers, and Codex
wants a TOML table.
The server exposes 24 tools in 10 groups: design, cost, validate, analyze, export, session, review, compliance, plan and migration. Full matrix in docs/integrations.md.
Offline commands grade, scan, compare, and plan
lint runs 10 anti-pattern checks. score grades 5 dimensions. analyze reports blast radius and single
points of failure. policy enforces policy-as-code with 9 built-in rules. security scans the spec and the
exported HCL. drift compares a design against a tfstate, and --remediate turns the gap into a cost,
compliance and plan preview.
review, compliance and plan are above. See docs/cli-reference.md.
Python API
from cloudwright import ArchSpec
from cloudwright.cost import CostEngine
from cloudwright.validator import Validator
from cloudwright.exporter import export_spec
spec = ArchSpec.from_file("spec.yaml")
priced = CostEngine().estimate(spec, workload_profile="medium")
findings = Validator().validate(spec, compliance=["hipaa", "pci-dss"])
hcl = export_spec(spec, "terraform", output_dir="./infra")
v1.10.0 adds migration planning with evidence-based closure
- One model covers the full estate. Infrastructure, data, applications, platforms, networks, facilities, and business services share one dependency graph.
- Dependencies determine the waves. The planner schedules prerequisites first, rejects cycles, checks rollback paths, and reports unresolved mappings.
- Closure needs evidence. Missing or failed blocking observations prevent closure and make
migrate verifyreturn exit code 2. - Industry rules stay outside the engine. Optional YAML packs add acceptance gates without adding industry fields to the core.
- PH telco is the first proof. The product remains industry-neutral. A manufacturing ERP fixture runs through the same planner with no domain pack.
Earlier releases added control-ID mapping and plan (v1.5.0), the self-correcting architect and OSCAL
(v1.6.0), cloudwright integrate (v1.7.0), the responsive dark-theme canvas (v1.8.0), and measured
canvas interaction fixes (v1.9.0). Full history in CHANGELOG.md.
Compatibility
- Python 3.12+
- Models: Anthropic (Claude Sonnet, Haiku) and OpenAI (GPT-5+ family), auto-detected from env.
- Clouds: AWS, GCP, Azure, Databricks. 114 service keys total.
- Install variants:
cloudwright-ai[cli],cloudwright-ai[web],cloudwright-ai-mcp.
Contributing, license, changelog
- Contributing guide: CONTRIBUTING.md
- License: MIT, see LICENSE
- Full release history: CHANGELOG.md
Preguntas sobre Cloudwright MCP
¿Cómo agrego Cloudwright MCP a Claude Code?
Ejecuta claude mcp add cloudwright -- uvx cloudwright-ai-mcp en tu terminal. Añade --scope user para que esté disponible en todos los proyectos.
¿Cómo agrego Cloudwright MCP a Cursor?
Abre ~/.cursor/mcp.json y añade el servidor en mcpServers, usando la configuración de Cursor que se muestra en la sección de instalación de arriba.
¿Qué proveedores de nube soporta Cloudwright?
Cubre AWS, GCP, Azure y Databricks a través de 114 claves de servicio.
¿Requiere Cloudwright una API key para todos los comandos?
No, solo los comandos design, modify, chat y adr llaman a un modelo. Todos los demás comandos se ejecutan offline y no necesitan una API key.
¿Qué tipo de código de infraestructura se puede exportar?
Puedes exportar a Terraform, OpenTofu, Pulumi (TypeScript o Python) y CloudFormation.
¿Puede Cloudwright ayudar con el cumplimiento normativo?
Sí, proporciona informes de cumplimiento mapeados con controles para frameworks como HIPAA, SOC 2, PCI-DSS, FedRAMP, GDPR, ISO 27001 y NIST 800-53.