What prerequisites are needed to use Alibaba Cloud Ops MCP Server?
You must install `uv`, have an Alibaba Cloud account with Access Key ID and Secret, and a compatible MCP client such as Cline or Cursor.
@aliyun
Basic information
AlibabaCloud CloudOps MCP Server
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"alibaba-cloud-ops-mcp-server": {
"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"
}
}
}
}RunCommand
DescribeVpcs
DescribeDBInstances
ListBuckets
GetCpuUsageData
LOCAL_ListDirectory
Alibaba Cloud Ops MCP Server is a Model Context Protocol (MCP) server that integrates with Alibaba Cloud APIs, enabling AI assistants to manage resources such as ECS, Cloud Monitor, OOS, OSS, VPC, and RDS, and to analyze, build, and deploy applications to Alibaba Cloud ECS instances.
Install uv, then configure the MCP client with the command uvx alibaba-cloud-ops-mcp-server@latest and set the environment variables ALIBABA_CLOUD_ACCESS_KEY_ID and ALIBABA_CLOUD_ACCESS_KEY_SECRET. Use a compatible MCP client like Cline, Cursor, or Qoder to interact with the server.
You must install `uv`, have an Alibaba Cloud account with Access Key ID and Secret, and a compatible MCP client such as Cline or Cursor.
Add a JSON configuration to your MCP client with the command `uvx alibaba-cloud-ops-mcp-server@latest` and provide the `ALIBABA_CLOUD_ACCESS_KEY_ID` and `ALIBABA_CLOUD_ACCESS_KEY_SECRET` environment variables.
The server supports ECS, VPC, RDS, OSS, Cloud Monitor, and OOS, with individual tools listed for each product.
Yes, it can analyze a project’s technology stack, build artifacts, upload them to OSS, and deploy to ECS instances using the OOS_CodeDeploy tool.
The server requires valid Alibaba Cloud Access Key credentials. No other limitations are mentioned in the README.
Hindsight: Agent Memory That Learns

Handl speaks the Model Context Protocol. Your whole billing operation — projects, invoices, clients, reports, approvals — as tools any AI assistant can call, inside your autonomy rules.

DeepMark helps teachers deliver rapid, consistent marking with meaningful feedback for every student — in a fraction of the time. What once took a week, now takes one free period.
🚀 The fast, Pythonic way to build MCP servers and clients.

Your AI assistant logs your meals and workouts, then plans your week from what you did. iPhone, Android and Garmin.
Comments