The Alibaba Cloud RDS OpenAPI MCP Server provides a Model Context Protocol server for interacting with Alibaba Cloud RDS services through OpenAPI. This tool allows you to easily manage your RDS instances and databases using MCP clients like Cherry Studio, Cline, or Claude.
uv
from Astral or the GitHub READMEuv python install 3.12
{
"mcpServers": {
"rds-openapi": {
"name": "rds-openapi",
"type": "stdio",
"description": "",
"isActive": true,
"registryUrl": "",
"command": "uvx",
"args": [
"alibabacloud-rds-openapi-mcp-server@latest"
],
"env": {
"ALIBABA_CLOUD_ACCESS_KEY_ID": "$you_access_id",
"ALIBABA_CLOUD_ACCESS_KEY_SECRET": "$you_access_key"
}
}
}
}
Set the required environment variables and run the MCP server:
# Set environment variables
export SERVER_TRANSPORT=sse;
export ALIBABA_CLOUD_ACCESS_KEY_ID=$you_access_id;
export ALIBABA_CLOUD_ACCESS_KEY_SECRET=$you_access_key;
export ALIBABA_CLOUD_SECURITY_TOKEN=$you_sts_security_token; # optional, required when using STS Token
# Run MCP server
uvx alibabacloud-rds-openapi-mcp-server@latest
After starting the server, you'll see:
INFO: Started server process [91594]
INFO: Waiting for application startup.
INFO: Application startup complete.
INFO: Uvicorn running on http://0.0.0.0:8000 (Press CTRL+C to quit)
Then configure Cline:
remote_server = "http://127.0.0.1:8000/sse";
git clone https://github.com/aliyun/alibabacloud-rds-openapi-mcp-server.git
"mcpServers": {
"rds-openapi-mcp-server": {
"command": "uv",
"args": [
"--directory",
"/path/to/alibabacloud-rds-openapi-mcp-server/src/alibabacloud_rds_openapi_mcp_server",
"run",
"server.py"
],
"env": {
"ALIBABA_CLOUD_ACCESS_KEY_ID": "access_id",
"ALIBABA_CLOUD_ACCESS_KEY_SECRET": "access_key",
"ALIBABA_CLOUD_SECURITY_TOKEN": "sts_security_token" // optional, required when using STS Token
}
}
}
The MCP server provides various tools for managing RDS instances:
create_db_instance
: Create a new RDS instancerestart_db_instance
: Restart an RDS instancemodify_db_instance_spec
: Modify RDS instance specificationsmodify_db_instance_description
: Change RDS instance descriptiondescribe_db_instances
: List all RDS instancesdescribe_db_instance_attribute
: Get detailed information about an instancedescribe_db_instance_performance
: Query performance datadescribe_error_logs
: Get error logs for an instancedescribe_slow_log_records
: Query slow log recordsdescribe_bills
: Get billing informationallocate_instance_public_connection
: Set up public connectiondescribe_db_instance_net_info
: View network configurationdescribe_vpcs
: List available VPCsdescribe_vswitches
: List available VSwitchesmodify_security_ips
: Update IP whitelistsdescribe_db_instance_ip_allowlist
: View IP whitelist configurationsattach_whitelist_template_to_instance
: Attach whitelist templatedescribe_all_whitelist_template
: List whitelist templatesdescribe_instance_linked_whitelist_template
: View linked templatescreate_db_instance_account
: Create an accountdescribe_db_instance_accounts
: List accountsdescribe_db_instance_databases
: List databasesget_current_time
: Get the current timeadd_tags_to_db_instance
: Add tags to an instancedescribe_available_classes
: View available instance classesdescribe_available_zones
: View available zonesmodify_parameter
: Change instance parametersdescribe_db_instance_parameters
: View parametersTo utilize the RDS MCP server in your AI assistant conversations, you can use the provided prompt template to guide the AI in helping you manage your RDS instances. The MCP tools can be used for various scenarios including:
The tools are automatically invoked by the AI assistant based on your requests, helping you manage your RDS instances efficiently.
There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json
file so that it is available in all of your projects.
If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json
file.
To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".
When you click that button the ~/.cursor/mcp.json
file will be opened and you can add your server like this:
{
"mcpServers": {
"cursor-rules-mcp": {
"command": "npx",
"args": [
"-y",
"cursor-rules-mcp"
]
}
}
}
To add an MCP server to a project you can create a new .cursor/mcp.json
file or add it to the existing one. This will look exactly the same as the global MCP server example above.
Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.
The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.
You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.