mcpField
A
alibabacloud-mcp-server

alibabacloud-mcp-server

Local
github.com/aliyunCloud & Infra135Updated 1d ago

About alibabacloud-mcp-server

An MCP server that lets AI assistants operate Alibaba Cloud resources through its APIs, covering ECS, Cloud Monitor, OOS, OSS, VPC and RDS. It also analyzes local projects and deploys applications to ECS instances. It is aimed at users managing Alibaba Cloud infrastructure from AI tools.

Key features

  1. 01ECS instance create, start, stop, reboot and delete
  2. 02VPC, RDS and OSS resource management
  3. 03Cloud Monitor CPU, memory and disk metrics
  4. 04Project stack analysis and application deployment

Use cases

  1. 01Viewing and managing Alibaba Cloud ECS instances through an AI assistant
  2. 02Packaging a local project and deploying it to ECS instances
  3. 03Querying resource usage metrics for ECS instances

MCP support

This is an MCP server that exposes tools for ECS, VPC, RDS, OSS, Cloud Monitor and deployment to MCP clients.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
"mcpServers": {
"alibabacloud-ecs": {
"command": "uvx",
"args": [
"alibabacloud-mcp-server@latest"
],
"env": {
"ALIBABA_CLOUD_ACCESS_KEY_ID": "<ALIBABA_CLOUD_ACCESS_KEY_ID>",
"ALIBABA_CLOUD_ACCESS_KEY_SECRET": "<ALIBABA_CLOUD_ACCESS_KEY_SECRET>"
}
}
}
}
Run commanduvx alibabacloud-mcp-server@latest
Environment variables to set
ALIBABA_CLOUD_ACCESS_KEY_IDSecret
ALIBABA_CLOUD_ACCESS_KEY_SECRETSecret

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
pypialibabacloud-mcp-server@latest

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

Alibaba Cloud Ops MCP Server

GitHub stars

中文版本

Alibaba Cloud Ops MCP Server is a Model Context Protocol (MCP) 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

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

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

Configuration

Use VS Code + Cline 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:

{
  "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

Know More

Tools

ProductToolFunctionImplementationStatus
ECSRunCommandRun CommandOOSDone
StartInstancesStart InstancesOOSDone
StopInstancesStop InstancesOOSDone
RebootInstancesReboot InstancesOOSDone
DescribeInstancesView InstancesAPIDone
DescribeRegionsView RegionsAPIDone
DescribeZonesView ZonesAPIDone
DescribeAvailableResourceView Resource InventoryAPIDone
DescribeImagesView ImagesAPIDone
DescribeSecurityGroupsView Security GroupsAPIDone
RunInstancesCreate InstancesOOSDone
DeleteInstancesDelete InstancesAPIDone
ResetPasswordModify PasswordOOSDone
ReplaceSystemDiskReplace Operating SystemOOSDone
VPCDescribeVpcsView VPCsAPIDone
DescribeVSwitchesView VSwitchesAPIDone
RDSDescribeDBInstancesList RDS InstancesAPIDone
StartDBInstancesStart the RDS instanceOOSDone
StopDBInstancesStop the RDS instanceOOSDone
RestartDBInstancesRestart the RDS instanceOOSDone
OSSListBucketsList BucketAPIDone
PutBucketCreate BucketAPIDone
DeleteBucketDelete BucketAPIDone
ListObjectsView object information in the bucketAPIDone
CloudMonitorGetCpuUsageDataGet CPU Usage Data for ECS InstancesAPIDone
GetCpuLoadavgDataGet CPU One-Minute Average Load Metric DataAPIDone
GetCpuloadavg5mDataGet CPU Five-Minute Average Load Metric DataAPIDone
GetCpuloadavg15mDataGet CPU Fifteen-Minute Average Load Metric DataAPIDone
GetMemUsedDataGet Memory Usage Metric DataAPIDone
GetMemUsageDataGet Memory Utilization Metric DataAPIDone
GetDiskUsageDataGet Disk Utilization Metric DataAPIDone
GetDiskTotalDataGet Total Disk Partition Capacity Metric DataAPIDone
GetDiskUsedDataGet Disk Partition Usage Metric DataAPIDone
Application ManagementOOS_CodeDeployDeploy applications to ECS instances with automatic artifact upload to OSSOOSDone
OOS_GetDeployStatusQuery deployment status of application groupsAPIDone
OOS_GetLastDeploymentInfoRetrieve information about the last deploymentAPIDone
LocalLOCAL_ListDirectoryList files and subdirectories in a directoryLocalDone
LOCAL_RunShellScriptExecute shell scripts or commandsLocalDone
LOCAL_AnalyzeDeployStackIdentify project deployment methods and technology stackLocalDone

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 (DingTalk group: 113455011677) for discussion.

README image

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.