# aliyun/alibaba-cloud-ops-mcp-server [Health: Active]

**Category:** ☁️ Cloud Platforms  
**Repository:** https://github.com/aliyun/alibaba-cloud-ops-mcp-server  
**GitHub Stars:** 129  
**Views:** 2  
**Installs:** 0  
**Upvotes:** 0  
**Directory Page:** https://allmcps.com/mcp/aliyun-alibaba-cloud-ops-mcp-server

## Description
A MCP server that enables AI assistants to operation resources on Alibaba Cloud, supporting ECS, Cloud Monitor, OOS and widely used cloud products.

## Tools
Capabilities this server exposes over MCP:

- **OOS_RunCommand** — 批量在多台ECS实例上运行云助手命令，适用于需要同时管理多台ECS实例的场景，如应用程序管理和资源标记操作等。
- **OOS_StartInstances** — 批量启动ECS实例，适用于需要同时管理和启动多台ECS实例的场景，例如应用部署和高可用性场景。
- **OOS_StopInstances** — 批量停止ECS实例，适用于需要同时管理和停止多台ECS实例的场景。
- **OOS_RebootInstances** — 批量重启ECS实例，适用于需要同时管理和重启多台ECS实例的场景。
- **OOS_RunInstances** — 批量创建ECS实例，适用于需要同时创建多台ECS实例的场景，例如应用部署和高可用性场景。
- **OOS_ResetPassword** — 批量修改ECS实例的密码，请注意，本操作将会重启ECS实例
- **OOS_ReplaceSystemDisk** — 批量替换ECS实例的系统盘，更换操作系统
- **OOS_StartRDSInstances** — 批量启动RDS实例，适用于需要同时管理和启动多台RDS实例的场景，例如应用部署和高可用性场景。
- **OOS_StopRDSInstances** — 批量停止RDS实例，适用于需要同时管理和停止多台RDS实例的场景。
- **OOS_RebootRDSInstances** — 批量重启RDS实例，适用于需要同时管理和重启多台RDS实例的场景。
- **OOS_CodeDeploy** — 
    将应用部署到阿里云ECS实例。使用阿里云OOS（运维编排服务）的CodeDeploy功能实现自动化部署。

    ## 前置条件（调用此工具前需完成）

    1. **识别项目类型**：读取项目配置文件（package.json、pom.xml、requirements.txt等），确定技术栈和部署语言（通过deploy_language参数传入）
    2. **构建部署产物**：执行构建命令生成压缩包（tar.gz、zip等），保存到 `.code_deploy/release` 目录
    3. **准备ECS实例**：确保目标ECS实例已创建，获取实例ID列表

    ## ⚠️ 重要提示：启动和停止命令参数

    **正常情况下，不需要提供 application_start 和 application_stop 参数！**
    
    - 系统会自动通过规则引擎分析部署文件和 deploy_language，自动生成启动和停止命令
    - 自动生成的命令包含所有必要的防御性检查（文件存在性、路径存在性等）
    - 自动生成的命令正确处理压缩包解压、目录切换、后台运行、日志重定向等
    - 对于 Node.js 应用，自动生成的命令会先执行 `npm install` 安装依赖
    
    **只有在以下情况下才需要手动提供这两个参数：**
    1. 用户明确指定了自定义的启动/停止命令
    2. 用户提供了关于启动/停止命令的特殊要求或说明
    
    **调用建议：直接调用工具，不传 application_start 和 application_stop 参数即可。**

    ## 自动生成的命令规范（供参考，了解即可）

    ### 1. 防御性命令设计
    自动生成的命令包含存在性检查，避免因路径/文件/命令不存在导致失败：
    - 压缩包：先检查文件存在再解压 `[ -f app.tar.gz ] && tar -xzf app.tar.gz || exit 1`
    - 可执行文件：检查文件存在再执行 `[ -f start.sh ] && chmod +x start.sh && ./start.sh || exit 1`
    - 命令可用性：检查命令是否存在 `command -v npm >/dev/null 2>&1 || exit 1`
    - 目录切换：先验证路径存在再切换 `[ -d dir ] && cd dir || exit 1`

    ### 2. 压缩包处理规范
    如果产物是压缩包，自动生成的命令会先解压：
    - 使用非交互式命令：`tar -xzf`、`unzip -o`（自动覆盖，无需确认）
    - 解压后执行启动命令，确保路径对应
    - 示例：`tar -xzf app.tar.gz && [ -d app ] && cd app && nohup java -jar app.jar > /root/app.log 2>&1 &`

    ### 3. 后台运行与日志
    自动生成的启动命令使用后台运行并重定向日志：
    - 格式：`nohup <command> > /root/app.log 2>&1 &`
    - 说明：nohup保持后台运行，`>` 重定向标准输出，`2>&1` 合并错误输出，`&` 后台执行

    ## 注意事项

    - 应用和应用分组会自动检查，已存在则跳过创建
    - 未提供ECS实例ID时，工具会返回创建引导链接
    - 部署信息自动保存到 `.code_deploy/.application.json`
    - project_path未提供时，会从file_path推断或使用当前目录
    - 部署完成后，以markdown格式展示service_link供用户跳转
    
- **OOS_GetLastDeploymentInfo** — 
    获取上次部署的应用信息
    
- **OOS_GetDeployStatus** — 
    查询应用分组的部署状态
    
- **CMS_GetCpuUsageData** — 获取ECS实例的CPU使用率数据
- **CMS_GetCpuLoadavgData** — 获取CPU一分钟平均负载指标数据
- **CMS_GetCpuloadavg5mData** — 获取CPU五分钟平均负载指标数据
- **CMS_GetCpuloadavg15mData** — 获取CPU十五分钟平均负载指标数据
- **CMS_GetMemUsedData** — 获取内存使用量指标数据
- **CMS_GetMemUsageData** — 获取内存利用率指标数据
- **CMS_GetDiskUsageData** — 获取磁盘利用率指标数据
- **CMS_GetDiskTotalData** — 获取磁盘分区总容量指标数据
- **CMS_GetDiskUsedData** — 获取磁盘分区使用量指标数据
- **OSS_ListBuckets** — 列出指定区域的所有OSS存储空间。
- **OSS_ListObjects** — 获取指定OSS存储空间中的所有文件信息。
- **OSS_PutBucket** — 创建一个新的OSS存储空间。
- **OSS_DeleteBucket** — 删除指定的OSS存储空间。
- **ECS_DescribeInstances** — 本接口支持根据不同请求条件查询实例列表，并关联查询实例的详细信息。
- **ECS_DescribeRegions** — 根据计费方式、资源类型等参数查询地域信息列表。
- **ECS_DescribeZones** — 根据地域ID、计费方式等参数查询可用区信息列表。
- **ECS_DescribeAccountAttributes** — 查询您在一个阿里云地域下能创建的ECS资源配额。包括您能创建的安全组数量、弹性网卡数量、按量付费vCPU核数、抢占式实例vCPU核数、按量付费云盘总容量配额、专用宿主机数量、网络类型以及账号是否已完成实名认证。
- **ECS_DescribeAvailableResource** — 查询指定可用区的资源库存状态。该接口主要用于在创建实例（RunInstances）或修改实例规格（ModifyInstanceSpec）前，确认目标资源（如实例规格、系统盘类型）在特定可用区是否库存充足。
- **ECS_DescribeImages** — 指定ImageId、镜像被使用场景、Filter过滤等参数，查询您可以使用的镜像资源列表。
- **ECS_DescribeSecurityGroups** — 本接口用于查询安全组基本信息列表，支持您通过地域、安全组ID、安全组类型等不同参数查询。
- **ECS_DeleteInstances** — 本接口用于批量删除或者释放按量付费实例或者到期的包年包月实例，支持通过参数设置决定云盘是否释放或转换为按量付费保留。
- **VPC_DescribeVpcs** — 查询已创建的VPC。
- **VPC_DescribeVSwitches** — 查询可组网的信息，内网按vswitch进行组网。
- **RDS_DescribeDBInstances** — 该接口用于查询RDS的实例列表。
- **LOCAL_ListDirectory** — 列出指定目录中的文件和子目录。返回包含名称、类型和大小等信息的目录和文件列表。
- **LOCAL_RunShellScript** — 执行 shell 脚本或命令。返回命令输出、错误信息和退出代码。注意：执行任意命令可能存在安全风险，请谨慎使用。
- **LOCAL_AnalyzeDeployStack** — 识别项目部署方式和技术栈。支持识别 npm、Python、Java、Go、Docker 等部署方式。

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

```json
"mcpServers": {
  "alibaba-cloud-ops-mcp-server": {
    "command": "uvx",
    "args": ["alibaba-cloud-ops-mcp-server@latest"],
    "env": {
      "ALIBABA_CLOUD_ACCESS_KEY_ID": "",
      "ALIBABA_CLOUD_ACCESS_KEY_SECRET": ""
    }
  }
}
```

**Requires environment variables:** `ALIBABA_CLOUD_ACCESS_KEY_ID`, `ALIBABA_CLOUD_ACCESS_KEY_SECRET` — the values above are empty placeholders; fill in real credentials before running (see the repository for what each one is for).

## Documentation & README

# Alibaba Cloud Ops MCP Server

[![GitHub stars](https://img.shields.io/github/stars/aliyun/alibaba-cloud-ops-mcp-server?style=social)](https://github.com/aliyun/alibaba-cloud-ops-mcp-server)

[中文版本](https://github.com/aliyun/alibaba-cloud-ops-mcp-server/blob/HEAD/README_zh.md)

Alibaba Cloud Ops MCP Server is a [Model Context Protocol (MCP)](https://modelcontextprotocol.io/introduction) server that provides seamless integration with Alibaba Cloud APIs, enabling AI assistants to operate resources on Alibaba Cloud, supporting ECS, Cloud Monitor, OOS, OSS, VPC, RDS and other widely used cloud products. It also enables AI assistants to analyze, build, and deploy applications to Alibaba Cloud ECS instances.

## MCP Maketplace Integration

* [Qoder](https://qoder.com) <a href="https://github.com/aliyun/alibaba-cloud-ops-mcp-server/blob/HEAD/qoder://aicoding.aicoding-deeplink/mcp/add?name=alibaba-cloud-ops-mcp-server&config=JTdCJTIyY29tbWFuZCUyMiUzQSUyMnV2eCUyMiUyQyUyMmFyZ3MlMjIlM0ElNUIlMjJhbGliYWJhLWNsb3VkLW9wcy1tY3Atc2VydmVyJTQwbGF0ZXN0JTIyJTVEJTJDJTIyZW52JTIyJTNBJTdCJTIyQUxJQkFCQV9DTE9VRF9BQ0NFU1NfS0VZX0lEJTIyJTNBJTIyWW91ciUyMEFjY2VzcyUyMEtleSUyMElkJTIyJTJDJTIyQUxJQkFCQV9DTE9VRF9BQ0NFU1NfS0VZX1NFQ1JFVCUyMiUzQSUyMllvdXIlMjBBY2Nlc3MlMjBLZXklMjBTRUNSRVQlMjIlN0QlN0Q%3D"><img src="https://raw.githubusercontent.com/aliyun/alibaba-cloud-ops-mcp-server/HEAD/image/qoder.svg" alt="Install MCP Server" height="20"></a>
* [Cursor](https://docs.cursor.com/tools) [![Install MCP Server](https://cursor.com/deeplink/mcp-install-dark.svg)](https://cursor.com/en/install-mcp?name=alibaba-cloud-ops-mcp-server&config=eyJ0aW1lb3V0Ijo2MDAsImNvbW1hbmQiOiJ1dnggYWxpYmFiYS1jbG91ZC1vcHMtbWNwLXNlcnZlckBsYXRlc3QiLCJlbnYiOnsiQUxJQkFCQV9DTE9VRF9BQ0NFU1NfS0VZX0lEIjoiWW91ciBBY2Nlc3MgS2V5IElkIiwiQUxJQkFCQV9DTE9VRF9BQ0NFU1NfS0VZX1NFQ1JFVCI6IllvdXIgQWNjZXNzIEtleSBTZWNyZXQifX0%3D)
* [Cline](https://cline.bot/mcp-marketplace)
* [ModelScope](https://www.modelscope.cn/mcp/servers/@aliyun/alibaba-cloud-ops-mcp-server?lang=en_US)
* [Lingma](https://lingma.aliyun.com/)
* [Smithery AI](https://smithery.ai/server/@aliyun/alibaba-cloud-ops-mcp-server)
* [FC-Function AI](https://cap.console.aliyun.com/template-detail?template=237)
* [Alibaba Cloud Model Studio](https://bailian.console.aliyun.com/?tab=mcp#/mcp-market/detail/alibaba-cloud-ops)

## Features

- **ECS Management**: Create, start, stop, reboot, delete instances, run commands, view instances, regions, zones, images, security groups, and more
- **VPC Management**: View VPCs and VSwitches
- **RDS Management**: List, start, stop, and restart RDS instances
- **OSS Management**: List, create, delete buckets, and view objects
- **Cloud Monitor**: Get CPU usage, load average, memory usage, and disk usage metrics for ECS instances
- **Application Deployment**: Deploy applications to ECS instances with automatic application and application group management
- **Project Analysis**: Automatically identify project technology stack and deployment methods (npm, Python, Java, Go, Docker, etc.)
- **Local File Operations**: List directories, run shell scripts, and analyze project structures
- **Dynamic API Tools**: Support for Alibaba Cloud OpenAPI operations

## Prepare

Install [uv](https://github.com/astral-sh/uv)

```bash
# On macOS and Linux.
curl -LsSf https://astral.sh/uv/install.sh | sh
```

## Configuration

Use [VS Code](https://code.visualstudio.com/) + [Cline](https://cline.bot/) to config MCP Server.

To use `alibaba-cloud-ops-mcp-server` MCP Server with any other MCP Client, you can manually add this configuration and restart for changes to take effect:

```json
{
  "mcpServers": {
    "alibaba-cloud-ops-mcp-server": {
      "timeout": 600,
      "command": "uvx",
      "args": [
        "alibaba-cloud-ops-mcp-server@latest"
      ],
      "env": {
        "ALIBABA_CLOUD_ACCESS_KEY_ID": "Your Access Key ID",
        "ALIBABA_CLOUD_ACCESS_KEY_SECRET": "Your Access Key SECRET"
      }
    }
  }
}
```

[For detailed parameter description, see MCP startup parameter document](https://github.com/aliyun/alibaba-cloud-ops-mcp-server/blob/HEAD/README_mcp_args.md)

## Know More

* [Alibaba Cloud Ops MCP Server is ready to use out of the box!！](https://developer.aliyun.com/article/1661348)
* [Setup Alibaba Cloud Ops MCP Server on Bailian](https://developer.aliyun.com/article/1662120)
* [Build your own Alibaba Cloud OpenAPI MCP Server with 10 lines of code](https://developer.aliyun.com/article/1662202)
* [Alibaba Cloud Ops MCP Server is officially available on the Alibaba Cloud Model Studio Platform MCP Marketplace](https://developer.aliyun.com/article/1665019)

## Tools

| **Product** | **Tool** | **Function** | **Implementation** | **Status** |
| --- | --- | --- | --- | --- |
| ECS | RunCommand | Run Command | OOS | Done |
| | StartInstances | Start Instances | OOS | Done |
| | StopInstances | Stop Instances | OOS | Done |
| | RebootInstances | Reboot Instances | OOS | Done |
| | DescribeInstances | View Instances | API | Done |
| | DescribeRegions | View Regions | API | Done |
| | DescribeZones | View Zones | API | Done |
| | DescribeAvailableResource | View Resource Inventory | API | Done |
| | DescribeImages | View Images | API | Done |
| | DescribeSecurityGroups | View Security Groups | API | Done |
| | RunInstances | Create Instances | OOS | Done |
| | DeleteInstances | Delete Instances | API | Done |
| | ResetPassword | Modify Password | OOS | Done |
| | ReplaceSystemDisk | Replace Operating System | OOS | Done |
| VPC | DescribeVpcs | View VPCs | API | Done |
| | DescribeVSwitches | View VSwitches | API | Done |
| RDS | DescribeDBInstances | List RDS Instances | API | Done |
|  | StartDBInstances | Start the RDS instance | OOS | Done |
|  | StopDBInstances | Stop the RDS instance | OOS | Done |
|  | RestartDBInstances | Restart the RDS instance | OOS | Done |
| OSS | ListBuckets | List Bucket | API | Done |
|  | PutBucket | Create Bucket | API | Done |
|  | DeleteBucket | Delete Bucket | API | Done |
|  | ListObjects | View object information in the bucket | API | Done |
| CloudMonitor | GetCpuUsageData | Get CPU Usage Data for ECS Instances | API | Done |
| | GetCpuLoadavgData | Get CPU One-Minute Average Load Metric Data | API | Done |
| | GetCpuloadavg5mData | Get CPU Five-Minute Average Load Metric Data | API | Done |
| | GetCpuloadavg15mData | Get CPU Fifteen-Minute Average Load Metric Data | API | Done |
| | GetMemUsedData | Get Memory Usage Metric Data | API | Done |
| | GetMemUsageData | Get Memory Utilization Metric Data | API | Done |
| | GetDiskUsageData | Get Disk Utilization Metric Data | API | Done |
| | GetDiskTotalData | Get Total Disk Partition Capacity Metric Data | API | Done |
| | GetDiskUsedData | Get Disk Partition Usage Metric Data | API | Done |
| Application Management | OOS_CodeDeploy | Deploy applications to ECS instances with automatic artifact upload to OSS | OOS | Done |
| | OOS_GetDeployStatus | Query deployment status of application groups | API | Done |
| | OOS_GetLastDeploymentInfo | Retrieve information about the last deployment | API | Done |
| Local | LOCAL_ListDirectory | List files and subdirectories in a directory | Local | Done |
| | LOCAL_RunShellScript | Execute shell scripts or commands | Local | Done |
| | LOCAL_AnalyzeDeployStack | Identify project deployment methods and technology stack | Local | Done |

## Deployment Workflow

The typical deployment workflow includes:

1. **Project Analysis**: Use `LOCAL_AnalyzeDeployStack` to identify the project's technology stack and deployment method
2. **Build Artifacts**: Build or package the application locally (e.g., create tar.gz or zip files)
3. **Deploy Application**: Use `OOS_CodeDeploy` to deploy the application to ECS instances
   - Automatically creates application and application group if they don't exist
   - Uploads artifacts to OSS
   - Deploys to specified ECS instances
4. **Monitor Deployment**: Use `OOS_GetDeployStatus` to check deployment status

## Contact us

If you have any questions, please join the [Alibaba Cloud Ops MCP discussion group](https://qr.dingtalk.com/action/joingroup?code=v1,k1,iFxYG4jjLVh1jfmNAkkclji7CN5DSIdT+jvFsLyI60I=&_dt_no_comment=1&origin=11) (DingTalk group: 113455011677) for discussion.

<img src="https://oos-public-cn-hangzhou.oss-cn-hangzhou.aliyuncs.com/alibaba-cloud-ops-mcp-server/Alibaba-Cloud-Ops-MCP-User-Group-en.png" width="500">