Automation CLI

MCP开发工具

提供方 未标注

开发工具 stdio · 本地进程 未标注 社区 / 第三方 Claude DesktopClaudeCursorVS Code
查看接入方式

一个命令行工具,用于将MCP服务器自动化部署到AWS ECS。

一句话选型结论

按资料字段整理

Automation CLI 属于开发工具类 MCP 服务器,stdio · 本地进程,鉴权方式未标注,可直接接入 Claude Desktop、Claude、Cursor 等,有可直接执行的安装命令。接入前先确认权限范围;涉及写入、删除或付款的操作,建议先在测试环境验证。

分类开发工具 传输方式stdio · 本地进程 鉴权未标注 部署方式本地部署
GitHub 星标 未标注 仓库热度,无公开仓库时显示未标注
工具数 未标注 暴露给模型的工具数量
资源 / 提示词 0 / 0 资源与提示词模板数量
维护方 社区 / 第三方 核验等级 仅资料核对

工具与能力

开发工具
数量来自来源目录的标注,具体工具清单以官方文档为准
工具数量未标注暴露给模型可调用的工具个数
资源数量0可读取的资源条目
提示词数量0内置提示词模板数量

能力标签

支持客户端

适用场景

开发

安装与配置

stdio · 本地进程 未标注
客户端在本机拉起子进程,数据不出本机
uvx

这条命令只是入口,具体启动参数请按官方文档补齐,不要直接照搬到别的服务器。

  1. 1
    准备运行环境

    stdio 服务在本地起进程,需要先装好 Node.js 等运行时,再按安装命令拉取依赖。

  2. 2
    安装服务

    复制上面的安装命令执行;命令里带占位符的位置,换成自己的密钥或路径。

  3. 3
    写入客户端配置

    在客户端的 MCP 配置里填好启动命令和参数,保存后完全退出客户端再打开,让新配置生效。

  4. 4
    验证是否可用

    连接成功后随便调一个只读工具,确认能返回结果,再接入正式流程。

典型使用场景

3 类
按分类与标签整理的常见用法,具体以官方文档为准
代码与仓库操作

在对话里直接查代码、提 issue、走 PR,省掉来回切工具。

本地命令与脚本

把构建、测试、格式化这类重复命令交给模型执行。

接口联调与测试

让模型调你的接口、跑一遍用例,快速定位问题。

选择建议

选之前先看这几条
按条目字段给出的判断,不替你决定用不用

值得选的地方

  • 有现成的安装命令,不用自己找入口,照着跑就能起服务。
  • 已适配 Claude Desktop、Claude、Cursor,换客户端不用重新研究配置。

先想清楚的地方

  • stdio 方式要求本地装好运行时(如 Node.js),换机器要重新装一遍。
  • 资料没标注工具数量,实际能力要装好后确认。
  • 版本更新与行为细节以官方仓库为准。

更适合

  • 需要在开发工具场景里让模型直接调用外部能力的人。
  • 已经在用 Claude Desktop、Claude 的用户,接入路径最短。
  • 想先快速试一下、能接受在本地或自有环境跑服务的人。

不太适合

  • 完全不想在本地装环境的人。
  • 需要厂商级 SLA 和技术支持的生产环境。

同类对比

6 个同类
同分类里挑最接近的几条,字段以各自详情页为准
MCP 服务器工具数传输方式部署方式安装命令最后核验
Automation CLI当前 未标注 stdio · 本地进程 本地部署 有 未标注
Git 838e2ec1 12 stdio · 本地进程 本地部署 有 2026-05-17
Markitdown MCP 2c653a5f 1 stdio · 本地进程 本地部署 有 2026-05-17
JavaGuide 未标注 stdio · 本地进程 本地部署 有 2026-04-11
awesome-claude-skills 未标注 stdio · 本地进程 本地部署 有 2026-04-26
Context7 831acf40 未标注 stdio · 本地进程 本地部署 有 2026-05-17

服务器档案

开发工具
字段来自项目仓库与公开索引,中文说明由本站标注
提供方未标注上游标注的维护方 未标注
分类开发工具本站按上游分类展示
连接方式stdio · 本地进程客户端在本机拉起子进程,数据不出本机
鉴权方式未标注远程服务建议用最小权限凭据
维护方社区 / 第三方核验等级 仅资料核对
包名 / 运行时未标注 · 未标注本地安装时用到的包标识与运行时
部署类型本地部署上游给出的部署形态
最近核验未标注上游最后核验时间

详细介绍

10.4 KB
来自项目仓库与上游目录的原文,未做删改

Migration Notice

This repo has been migrated to aws-samples. New repo path is https://github.com/aws-samples/sample-mcp-server-automation . This repo is archived.

MCP Server Automation CLI

A powerful CLI tool that automates the process of transforming Model Context Protocol (MCP) stdio servers into Docker images deployed on AWS ECS using mcp-proxy. This tool bridges the gap between local MCP servers and remote HTTP-based deployments.

🚀 Features

  • 🔄 Automatic Build: Fetch MCP servers from GitHub, build Docker images, and push to ECR
  • ☁️ One-Click Deploy: Generate CloudFormation templates and deploy complete ECS infrastructure
  • 🔍 Smart Detection: Automatically detect MCP server commands from README files
  • 🐳 Multi-Architecture: Support for Python, Node.js, and hybrid MCP servers
  • 🔧 Debug Support: Built-in debug logging for troubleshooting
  • 📝 Config Generation: Generate MCP client configurations for Claude Desktop, Cline, etc.

📋 Prerequisites

  • Python 3.8+
  • Docker (with daemon running)
  • AWS CLI configured with appropriate permissions
  • AWS ECR repository (created if using ECR push)
  • AWS ECS cluster (created if deploying)

Install uv```bash

On macOS and Linux.

curl -LsSf https://astral.sh/uv/install.sh | sh
``````powershell

On Windows.

powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"


## 📖 Quick Start

### Using uvx (Recommended)

The easiest way to use this tool is with `uvx`, which handles dependencies automatically:```bash
# Install from a Git repository
uvx --from git+https://github.com/aws-samples/sample-mcp-server-automation mcp-server-automation --config your-config.yaml

Local Development Setup```bash

Clone and setup

git clone <repository-url>
cd mcp-convert-automate

Create virtual environment and install dependencies

python -m venv venv
source venv/bin/activate # Windows: venv\Scripts\activate
pip install -r requirements.txt

Install in development mode (optional - for local CLI usage)

pip install -e .


## ⚙️ Configuration

The tool uses a unified YAML configuration file with `build` and `deploy` sections.

### Unified Configuration```yaml
build:
  # Required: GitHub repository URL
  github_url: &quot;https://github.com/awslabs/mcp&quot;

  # Optional: Subfolder if MCP server is not in root
  subfolder: &quot;src/aws-documentation-mcp-server&quot;

  # Optional: Git branch to build from (default: main)
  branch: &quot;main&quot;

  # Required for deployment: Must be true to enable ECR push and deployment
  push_to_ecr: true

  # Optional: Custom Docker image configuration
  # If not specified, auto-generated when push_to_ecr=true
  # image:
  #   repository: &quot;123456789012.dkr.ecr.us-east-1.amazonaws.com/mcp-servers/my-mcp-server&quot;
  #   tag: &quot;v1.0&quot;  # Optional, defaults to dynamic git-based tag

  # Optional: AWS region (default: from AWS profile, fallback to us-east-1)
  # aws_region: &quot;us-west-2&quot;

  # Optional: Custom Dockerfile path
  # dockerfile_path: &quot;./custom.Dockerfile&quot;

  # Optional: Override auto-detected MCP server command
  # Required when README only contains Docker commands or no suitable command is found
  # command_override:
  #   - &quot;python&quot;
  #   - &quot;-m&quot;
  #   - &quot;my_server_module&quot;
  #   - &quot;--verbose&quot;

  # Optional: Set environment variables in the container
  # environment_variables:
  #   LOG_LEVEL: &quot;debug&quot;
  #   AWS_REGION: &quot;us-east-1&quot;
  #   MCP_SERVER_NAME: &quot;custom-server&quot;

deploy:
  # Required: Enable deployment (only works when push_to_ecr=true)
  enabled: true

  # Required: ECS service name
  service_name: &quot;my-mcp-service&quot;

  # Required: ECS cluster name
  cluster_name: &quot;my-ecs-cluster&quot;

  # Required: VPC ID where resources will be created
  vpc_id: &quot;vpc-12345678&quot;

  # Required: Subnet configuration
  alb_subnet_ids:    # Public subnets for ALB (minimum 2 in different AZs)
    - &quot;subnet-public-1&quot;
    - &quot;subnet-public-2&quot;
  ecs_subnet_ids:    # Private subnets for ECS tasks (minimum 1, should resides in AZ of alb_subnet_ids)
    - &quot;subnet-private-1&quot;
    - &quot;subnet-private-2&quot;

  # Optional: Container port (default: 8000)
  port: 8000

  # Optional: Task CPU units (default: 256)
  cpu: 256

  # Optional: Task memory in MB (default: 512)
  memory: 512

  # Optional: SSL certificate ARN for HTTPS
  certificate_arn: &quot;arn:aws:acm:us-east-1:123456789012:certificate/12345678-1234-1234-1234-123456789012&quot;

  # Optional: Save MCP client configuration to file
  save_config: &quot;./mcp-config.json&quot;

🏗️ Architecture

Build Process Flow

  1. Repository Analysis: Downloads GitHub repos and detects MCP server configuration from README files
  2. Command Detection: Parses JSON blocks in README files to extract MCP server start commands, prioritizing NPX/uvx over Docker commands
  3. Dockerfile Generation: Uses Jinja2 templates to create multi-stage Docker builds with mcp-proxy CLI integration
  4. Image Building: Creates hybrid Node.js + Python containers with proper dependency management

Deployment Architecture```

GitHub Repo → Docker Build → ECR → ECS Fargate ← ALB ← Internet
↓ ↓ ↓ ↓ ↓
MCP Server → mcp-proxy + MCP → Image → Service → HTTP/SSE Endpoints


### Key Technical Details

- **mcp-proxy Integration**: Uses TypeScript/Node.js CLI tool for HTTP transport with debug logging enabled
- **Container Architecture**: Multi-stage builds with `node:24-bullseye` base image, includes netcat for health checks
- **Command Format**: `mcp-proxy --debug --port 8000 --shell  [-- ]` for proper argument ordering
- **Transport Protocol**: Converts MCP stdio to HTTP with `/mcp` endpoint for Streamable HTTP transport
- **Dynamic Tagging**: Images tagged with git commit hash and timestamp (e.g., `a1b2c3d4-develop-20231222-143055`)
- **Branch Support**: Can build from specific git branches, defaults to &#x27;main&#x27;
- **Health Checks**: Container uses netcat port checking, ALB health checks `/mcp` endpoint expecting HTTP 400
- **MCP Config Generation**: Automatically generates and prints MCP client configuration after deployment
- **Infrastructure**: Complete CloudFormation stack with VPC, ALB, ECS Fargate, security groups, and IAM roles

## 🔧 Advanced Usage

### Custom Dockerfile```yaml
build:
  github_url: &quot;https://github.com/my-org/custom-mcp-server&quot;
  dockerfile_path: &quot;./custom/Dockerfile&quot;
  push_to_ecr: true
deploy:
  enabled: true
  # ... deployment configuration

Command Detection and Override

The tool automatically detects MCP server startup commands from:
1. README files - JSON configuration blocks with mcpServers
2. pyproject.toml - Console scripts or main modules
3. setup.py - Entry points and scripts

Command Override Required When:
- README only contains Docker commands (not suitable for containerization)
- No suitable startup command can be detected
- You want to specify exact startup parameters

Example:```yaml
build:
github_url: "https://github.com/my-org/custom-mcp-server"
command_override:
- "python"
- "-m"
- "my_server_module"
- "--verbose"
- "--port"
- "3000"
push_to_ecr: true


**Error Example:**
If your MCP server README only shows:```json
{
  &quot;mcpServers&quot;: {
    &quot;myserver&quot;: {
      &quot;command&quot;: &quot;docker&quot;,
      &quot;args&quot;: [&quot;run&quot;, &quot;myserver:latest&quot;]
    }
  }
}

You'll get an error requiring command_override to specify the direct startup command.

Environment Variables in Container

Set custom environment variables that will be available to the MCP server at runtime:```yaml
build:
github_url: "https://github.com/my-org/custom-mcp-server"
environment_variables:
LOG_LEVEL: "debug"
AWS_REGION: "us-east-1"
MCP_SERVER_NAME: "custom-server"
PYTHONPATH: "/app/mcp-server:/custom/path"
push_to_ecr: true


### System Environment Variables

Set environment variables to override default AWS settings:```bash
export AWS_REGION=us-west-2
export ECS_CLUSTER_NAME=my-production-cluster

🐛 Troubleshooting

Docker Build Issues

  • Ensure Docker daemon is running
  • Check that the MCP server has proper dependency files (requirements.txt, pyproject.toml, etc.)
  • Verify GitHub repository URL is accessible

ECR Push Issues

  • Ensure AWS credentials have ECR permissions
  • Verify ECR repository exists and is accessible
  • Check that Docker is authenticated with ECR

CloudFormation Deployment Issues

  • Ensure AWS credentials have sufficient permissions
  • Check that the ECS cluster exists
  • Verify AWS region is correct
  • Review CloudFormation events in AWS Console for detailed error messages

MCP Server Connection Issues

  • Check container logs: docker logs
  • Verify health check endpoint: curl http:///mcp (expects HTTP 400)
  • Test direct connection: curl http:///mcp
  • Use debug mode for detailed logging

🔐 AWS Permissions Required

The AWS credentials used must have the following permissions:

ECR Permissions```json

{
"Version": "2012-10-17",
"Statement": [
{
"Effect": "Allow",
"Action": [
"ecr:BatchCheckLayerAvailability",
"ecr:GetDownloadUrlForLayer",
"ecr:BatchGetImage",
"ecr:GetAuthorizationToken",
"ecr:PutImage",
"ecr:InitiateLayerUpload",
"ecr:UploadLayerPart",
"ecr:CompleteLayerUpload"
],
"Resource": "*"
}
]
}


### ECS and CloudFormation Permissions```json
{
  &quot;Version&quot;: &quot;2012-10-17&quot;,
  &quot;Statement&quot;: [
    {
      &quot;Effect&quot;: &quot;Allow&quot;,
      &quot;Action&quot;: [
        &quot;ecs:*&quot;,
        &quot;cloudformation:*&quot;,
        &quot;ec2:*&quot;,
        &quot;elasticloadbalancing:*&quot;,
        &quot;iam:CreateRole&quot;,
        &quot;iam:AttachRolePolicy&quot;,
        &quot;iam:PassRole&quot;,
        &quot;logs:CreateLogGroup&quot;,
        &quot;logs:DescribeLogGroups&quot;
      ],
      &quot;Resource&quot;: &quot;*&quot;
    }
  ]
}

📝 MCP Client Configuration

After deployment, the tool generates configuration for MCP clients:```json
{
"mcpServers": {
"my-mcp-server": {
"type": "sse",
"url": "http://<ALB address>/sse"
}
}
}


### Testing MCP Connection```bash
# Install mcp-proxy client
npm install -g mcp-proxy

# Test connection
mcp-proxy https://your-alb-url.amazonaws.com/mcp

Security

See CONTRIBUTING for more information.

License

This library is licensed under the MIT-0 License. See the LICENSE file.

🆘 Support

  • Check the troubleshooting section for common issues
  • Review CloudFormation events in AWS Console for deployment issues
  • Use debug mode for detailed logging
  • Open an issue for bugs or feature requests

常见问题

8 问
答案由本站依据条目字段整理,不引用上游原文
Automation CLI 怎么安装?

在客户端按下面的安装命令接入:uvx。装完在客户端配置里引用同一个包或端点。

Automation CLI 怎么在 Claude Desktop、Claude、Cursor 里配置?

它的传输方式是stdio · 本地进程,在客户端的 MCP 配置里填好启动命令和参数,保存后完全退出客户端再打开,配置才会生效。

Automation CLI 收费吗?

本站不代收费用,也没有标注具体价格。是否收费取决于服务本身和背后的接口额度,正式使用前按官方说明确认。

Automation CLI 需要 API Key 吗?

资料没有标注鉴权方式,是否需要密钥取决于服务本身,接入前按官方文档确认。

Automation CLI 支持哪些客户端?

资料标注支持 Claude Desktop、Claude、Cursor、VS Code、Cline、Gemini CLI;其他客户端只要能配置 MCP Server,也能用同样的命令或地址接入。

Automation CLI 能提供哪些能力?

资料显示能力标签包括 开发。具体工具清单以官方文档为准。

Automation CLI 需要什么运行环境?

属于本地进程,需要在本机装好运行环境。

Automation CLI 是本地还是远程?

它是本地进程(stdio),由客户端在本机拉起。传输方式为stdio · 本地进程。

热门专题

按标签挑服务器
全部专题 →

服务器信息以作者仓库与官方文档为准;分类、传输方式与鉴权方式的中文说明为中文整理,最近核验 未标注。