What IDEs are supported?
Supported IDEs include Cursor, Windsurf, Codex, VS Code, VS Code Insiders, and Claude Desktop.
@DefangLabs
基本信息
Defang CLI. Develop Once, Deploy Anywhere. Take your app from Docker Compose to a secure and scalable deployment on your favorite cloud in minutes.
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"defang": {
"command": "npx",
"args": [
"-y",
"defang@latest",
"mcp",
"serve"
]
}
}
}Create a defang stack file to deploy to AWS
Create a defang stack file to deploy to Azure
Create a defang stack file to deploy to GCP
Get the currently selected stack
Initiate deployment of the application stack defined in the docker-compose files in the current working directory
Destroy the deployed application in the selected stack, defined in the docker-compose files in the current working directory
Estimate the cost of deploying a Defang project to AWS or GCP
List config variables for the currently selected stack in the Defang project
List all the Defang stack(s) for the current project
Fetch logs for the application in the selected stack, in pages of up to 100 lines. You can use the 'since' and 'until' parameters to page through logs by time.
Get the current project name
Remove a config variable from the currently selected stack in the Defang project
Select the deployment stack for the Defang project
List deployed services for the selected project stack in the current working directory
Set a config variable for the currently selected stack in the Defang project
The Defang MCP Server is an MCP server equipped with Defang tools (deploy, services, destroy) to help users manage their services seamlessly using AI coding agents within supported IDEs.
Install the npm package manager, then run npx -y defang@latest mcp setup --client=<your-ide> to connect to your IDE. After setup, start the server with npx -y defang@latest mcp serve. You can then access the Defang MCP tools through the AI agent chat in your IDE.
Supported IDEs include Cursor, Windsurf, Codex, VS Code, VS Code Insiders, and Claude Desktop.
The `deploy` tool scans your project directory for Dockerfiles and `compose.yaml` files, then deploys the detected service(s) using Defang. Deployment progress can be monitored in the Defang Portal.
Run `npx -y defang@latest mcp setup --client=<your-ide>` for your preferred IDE, then start the server with `npx -y defang@latest mcp serve`.
The `services` tool shows Service Name, Deployment ID, Public URL, and Service Status for all currently deployed services.
Given a project name or directory, the `destroy` tool identifies and terminates all services deployed with Defang.
The Terraform MCP Server provides seamless integration with Terraform ecosystem, enabling advanced automation and interaction capabilities for Infrastructure as Code (IaC) development.
Development environments for coding agents. Enable multiple agents to work safely and independently with your preferred stack.
The official MCP server for Muumuu Domain by GMO Pepabo, Inc — the first remote MCP server in the Japanese domain registrar industry. Search and register domains, manage owned domains and contracts, and configure DNS rec

Your AI can finally reach the physical world. Kilo is an AI-first IoT platform for commercial and industrial operations, and this connector hands a live deployment to the AI client you already use. Not an export. Not a
Model Context Protocol (MCP) server for Kubernetes and OpenShift
评论