alibabacloud-rds-openapi
MCP server for RDS Services via OPENAPI.
claude mcp add --transport stdio aliyun-alibabacloud-rds-openapi-mcp-server uvx alibabacloud-rds-openapi-mcp-server@latest \ --env ALIBABA_CLOUD_ACCESS_KEY_ID="$you_access_id" \ --env ALIBABA_CLOUD_ACCESS_KEY_SECRET="$you_access_key"
How to use
This MCP server provides a set of OpenAPI-based tools for managing Alibaba Cloud RDS instances. It exposes a collection of OpenAPI tools under the rds-openapi suite, including actions to describe instances, modify configurations, manage security IP whitelists, and perform various database-related operations. The server runs as an MCP through uv/uvx, allowing you to enable or disable specific toolsets to tailor capabilities to your needs. You can also utilize the included SQL tools to execute read-only SQL statements and retrieve results in a controlled, ephemeral manner as part of automated workflows. When using this server, you will authenticate with Alibaba Cloud credentials (AK/SK) and optionally provide an API key for MCP-level request filtering. The toolsets can be configured to limit exposure to only the required subset of OpenAPI operations, helping to minimize risk while integrating with your workflows.
How to install
Prerequisites:
- Install uv from Astral (uv) or via the recommended installation method in the uv documentation.
- Install Python (recommended: Python 3.12) and ensure it is available on your PATH.
- Alibaba Cloud credentials with access to RDS services.
Step-by-step installation:
- Install uv (if not already installed) following the uv installation guide:
# Example (if using a system package manager or provided installer)
# Refer to the Astral uv docs for exact commands for your OS
- Install Python 3.12 (or a compatible version) and ensure python is accessible:
# On Unix-like systems
pyenv install 3.12.0
pyenv global 3.12.0
- Install the MCP server package via npm/yarn/cherrystudio workflow as described in the README:
# Using uv with the OpenAPI MCP server via the example configuration
# No additional installation is required beyond uv; ensure you have network access to pull the server package
- Prepare your environment variables:
export ALIBABA_CLOUD_ACCESS_KEY_ID=your_access_id
export ALIBABA_CLOUD_ACCESS_KEY_SECRET=your_access_key
# Optional, if using STS
export ALIBABA_CLOUD_SECURITY_TOKEN=your_sts_token
# Optional for API Key protection
export API_KEY=your_mcp_server_api_key
- Run the MCP server via uvx (as shown in the Quick Start examples):
uvx alibabacloud-rds-openapi-mcp-server@latest
- If you are using Claude/Cline style configuration, ensure your MCP client is pointed at the running server's address (e.g., http://127.0.0.1:8000) as described in the documentation.
Additional notes
Tips and considerations:
- Ensure Alibaba Cloud credentials have the necessary RDS permissions for the actions you plan to perform.
- If you encounter 401 errors related to API keys, verify API_KEY configuration and the server’s authentication settings.
- The toolsets (MCP_TOOLSETS) let you enable only the needed tools (e.g., rds, rds_custom_read). By default, the rds group is loaded if no toolset is specified.
- When using STS tokens, remember to refresh tokens as needed; you can supply ALIBABA_CLOUD_SECURITY_TOKEN if required.
- For security, avoid exposing your AK/SK in logs or shared configurations. Use environment variables and secret managers where possible.
- The OpenAPI Tools list includes a wide range of operations (describe_db_instance, modify_db_instance, restart_db_instance, etc.). Review the list to determine which tools you need for your automation.
- If importing the configuration into Cherry-studio or another MCP client, ensure the server name and command match the MCP client’s expectations (e.g., using uvx with the latest package).
Related MCP Servers
mysql_mcp_server
A Model Context Protocol (MCP) server that enables secure interaction with MySQL databases
jupyter
🪐 🔧 Model Context Protocol (MCP) Server for Jupyter.
edumcp
EDUMCP is a protocol that integrates the Model Context Protocol (MCP) with applications in the education field, dedicated to achieving seamless interconnection and interoperability among different AI models, educational applications, smart hardware, and teaching AGENTs.
lihil
2X faster ASGI web framework for python, offering high-level development, low-level performance.
MCP2Lambda
Run any AWS Lambda function as a Large Language Model (LLM) tool without code changes using Anthropic's Model Context Protocol (MCP).
packt-netops-ai-workshop
🔧 Build Intelligent Networks with AI