# containerization-assist [Official] [Health: Active]

**Category:** ☁️ Cloud Platforms  
**Repository:** https://github.com/Azure/containerization-assist  
**GitHub Stars:** 45  
**npm Downloads (last month):** 1854  
**Views:** 2  
**Installs:** 0  
**Upvotes:** 0  
**Directory Page:** https://allmcps.com/mcp/containerization-assist

## Description
TypeScript MCP server for AI-powered containerization workflows with Docker and Kubernetes support

## Tools
Capabilities this server exposes over MCP:

- **analyze-repo** — Analyze repository structure and detect technologies by parsing config files
- **generate-dockerfile** — Gather insights from knowledge base and return requirements for Dockerfile creation
- **fix-dockerfile** — Analyze Dockerfile for issues including organizational policy validation and return knowledge-based fix recommendations
- **build-image-context** — Prepare Docker build context with security analysis and return build commands
- **scan-image** — Scan Docker images for security vulnerabilities with remediation guidance (uses Trivy CLI)
- **tag-image** — Tag Docker images with version and registry information
- **push-image** — Push Docker images to a registry
- **generate-k8s-manifests** — Gather insights and return requirements for Kubernetes/Helm/ACA/Kustomize manifest creation
- **prepare-cluster** — Prepare Kubernetes cluster for deployment
- **verify-deploy** — Verify Kubernetes deployment status
- **ops** — Operational utilities for ping and server status
- **create-containerization-policy** — Step-by-step guidance for authoring a custom OPA Rego policy
- **kind-loop** — Local dev loop: analyze → build → scan → deploy to Kind
- **aks-loop** — Remote dev loop: analyze → build → push → deploy to AKS

## Claude Desktop Quick Installation
Install path detected from listing signals. Uses `npx` (confidence: high):

```json
"mcpServers": {
  "containerization-assist": {
    "command": "npx",
    "args": ["-y","containerization-assist-mcp"]
  }
}
```

## Documentation

## What containerization-assist does

The containerization-assist MCP server provides MCP tools for taking an application from repository analysis through container build, security review, and Kubernetes deployment. Its repository analysis detects technologies by parsing configuration files. Dockerfile and Kubernetes-related tools return requirements and recommendations informed by a knowledge base rather than directly describing an unexamined project.

The workflow covers Docker image preparation, vulnerability scanning, tagging, registry pushes, Kubernetes or Helm manifest generation, cluster preparation, and deployment verification. It also includes operational status utilities and a guided tool for creating custom OPA Rego containerization policies. The server belongs in the Developer Tools category and is intended for use from VS Code, Claude Desktop, or another MCP-compatible client.

## How it works

Tools are designed for sequential use, with later steps using results from earlier operations. A typical application flow starts with `analyze-repo`, continues through Dockerfile generation and image-context preparation, then scans and tags the image before generating Kubernetes manifests. Cluster preparation and deployment verification complete the process when Kubernetes is available.

`kind-loop` combines analysis, building, scanning, and deployment for a local Kind environment. `aks-loop` provides the corresponding remote sequence for analysis, building, pushing, and deployment to AKS. The server reports progress through MCP notifications and validates prerequisites early when Docker or Kubernetes access is unavailable. Repository analysis and generation tools also support detected monorepo structures, while safeguards exclude shared libraries and utility directories from containerization.

The policy system can set defaults such as resource values, base images, and build strategy before generation. It can also filter or weight knowledge, inject templates, perform semantic checks, assess security, and check consistency between tools. Included policy examples cover environment-based strategies, team-tier cost controls, security-first rules, multi-cloud registry governance, and development speed optimization.

## Setup and configuration

The containerization-assist MCP server requires Node.js 20 or later and a running Docker daemon or Docker Desktop. Add it to an MCP client with a command equivalent to `npx -y containerization-assist-mcp start`; the documented example sets `LOG_LEVEL` to `info`. On Windows, Docker access can use `DOCKER_SOCKET=//./pipe/docker_engine`.

Trivy is optional but required for image security scanning. Kubernetes deployment tools require a usable kubeconfig, cluster connectivity, and suitable RBAC permissions. The repository documents direct SDK usage as an alternative to the MCP protocol, including imports for repository analysis, build-context preparation, and image scanning.

## Tools and capabilities

- Analyze repository structure and detect technologies with `analyze-repo`.
- Generate Dockerfile and Kubernetes, Helm, Azure Container Apps, or Kustomize requirements.
- Inspect Dockerfiles and return policy-aware, knowledge-based fix recommendations.
- Prepare Docker build contexts with security analysis and build commands.
- Scan images with Trivy and provide remediation guidance.
- Tag and push images using version and registry information.
- Prepare clusters, verify deployments, and expose ping and status operations.
- Create containerization policies and run Kind or AKS development loops.

## Limitations and notes

The containerization-assist MCP server is optimized for one engineer containerizing one application at a time. Its model is sequential, so workflows depend on earlier tool results. Docker features need an accessible Docker socket, while deployment features need a reachable Kubernetes cluster and appropriate permissions. Trivy-based scanning is unavailable unless Trivy is installed. Generated content is guided by built-in prompts, knowledge, and optional policies; the tools return requirements, recommendations, commands, or workflow results rather than removing the need to review and execute them in the target environment.

_Full upstream README: https://allmcps.com/mcp/containerization-assist/readme_