AnalyticDB For MySQL MCP Server

What is AnalyticDB For MySQL MCP Server about?

Enables seamless communication between AI agents and AnalyticDB for MySQL clusters, exposing tools to query metadata, execute SQL statements, and obtain execution plans.

How to use AnalyticDB For MySQL MCP Server?

1. Installation
   • Clone the repository and run the server with uv, or install via pip install adb-mysql-mcp-server.
2. Configuration
   • Add an entry to the MCP client configuration file specifying the command, arguments, and required environment variables (ADB_MYSQL_HOST, ADB_MYSQL_PORT, ADB_MYSQL_USER, ADB_MYSQL_PASSWORD, ADB_MYSQL_DATABASE).
3. Interaction
   • Use the defined resources (e.g., adbmysql:///databases, adbmysql:///{schema}/tables) and tools (execute_sql, get_query_plan, get_execution_plan) within your AI agent workflow.

Key features

• SQL Execution: Run arbitrary SQL queries on AnalyticDB for MySQL clusters.
• Query Planning: Retrieve logical and physical query plans with runtime statistics.
• Metadata Access: Built‑in resources to list databases, tables, DDL scripts, and configuration values.
• Dual Deployment Modes: Local repository mode (using uv) and pip package mode for quick setup.
• Debug Support: Integration with MCP Inspector for local debugging.

Use cases

• AI agents that need to explore database schemas before generating code.
• Automated data analysis pipelines that query AnalyticDB for MySQL directly.
• Monitoring tools that fetch execution plans to optimize query performance.
• Development of custom MCP servers extending the provided tools and resources.

FAQ

Q: Which command should I use to start the server? A: In local mode run uv --directory /path/to/alibabacloud-adb-mysql-mcp-server run adb-mysql-mcp-server. In pip mode use uv run --with adb-mysql-mcp-server adb-mysql-mcp-server.

Q: Do I need Node.js? A: Node.js is only required if you want to run the MCP Inspector (npx @modelcontextprotocol/inspector). The server itself is Python‑based.

Q: What environment variables are mandatory? A: ADB_MYSQL_HOST, ADB_MYSQL_PORT, ADB_MYSQL_USER, ADB_MYSQL_PASSWORD, and ADB_MYSQL_DATABASE must be set for the server to connect to the AnalyticDB for MySQL cluster.

Q: Can I extend the server with custom tools? A: Yes, the project is open‑source; you can add new Python modules that expose additional functionality to the MCP client.

Q: Is there a built‑in way to retrieve table DDL? A: Use the resource template adbmysql:///{database}/{table}/ddl to get the DDL script for a specific table.

AnalyticDB for MySQL MCP Server

AnalyticDB for MySQL MCP Server serves as a universal interface between AI Agents and AnalyticDB for MySQL databases. It enables seamless communication between AI Agents and AnalyticDB for MySQL, helping AI Agents retrieve AnalyticDB for MySQL database metadata and execute SQL operations.

1. MCP Client Configuration

Mode 1: Using Local File

• Download the GitHub repository

git clone https://github.com/aliyun/alibabacloud-adb-mysql-mcp-server

• MCP Integration

Add the following configuration to the MCP client configuration file:

{
  "mcpServers": {
    "adb-mysql-mcp-server": {
      "command": "uv",
      "args": [
        "--directory",
        "/path/to/alibabacloud-adb-mysql-mcp-server",
        "run",
        "adb-mysql-mcp-server"
      ],
      "env": {
        "ADB_MYSQL_HOST": "host",
        "ADB_MYSQL_PORT": "port",
        "ADB_MYSQL_USER": "database_user",
        "ADB_MYSQL_PASSWORD": "database_password",
        "ADB_MYSQL_DATABASE": "database"
      }
    }
  }
}

Mode 2: Using PIP Mode

• Installation

Install MCP Server using the following package:

pip install adb-mysql-mcp-server

• MCP Integration

Add the following configuration to the MCP client configuration file:

 {
  "mcpServers": {
    "adb-mysql-mcp-server": {
      "command": "uv",
      "args": [
        "run",
        "--with",
        "adb-mysql-mcp-server",
        "adb-mysql-mcp-server"
      ],
      "env": {
        "ADB_MYSQL_HOST": "host",
        "ADB_MYSQL_PORT": "port",
        "ADB_MYSQL_USER": "database_user",
        "ADB_MYSQL_PASSWORD": "database_password",
        "ADB_MYSQL_DATABASE": "database"
      }
    }
  }
}

2. Develop your own AnalyticDB for MySQL MCP server

If you want to develop your own AnalyticDB for MySQL MCP Server, you can install the python dependency packages using the following command:

1. Download the source code from GitHub.
2. Install uv package manager.
3. Install Node.js which provides a node package tool whose name is npx
4. Install the python dependencies in the root diretory of the project using the following command:

uv pip install -r pyproject.toml 

5. If you want to debug the mcp server locally, you could start up an MCP Inspector using the following command:

npx @modelcontextprotocol/inspector  \
-e ADB_MYSQL_HOST=your_host \
-e ADB_MYSQL_PORT=your_port \
-e ADB_MYSQL_USER=your_username \
-e ADB_MYSQL_PASSWORD=your_password \
-e ADB_MYSQL_DATABASE=your_database \
uv --directory /path/to/alibabacloud-adb-mysql-mcp-server run adb-mysql-mcp-server 

3. Introduction to the components of AnalyticDB for MySQL MCP Server

• Tools

  • execute_sql: Execute a SQL query in the AnalyticDB for MySQL Cluster

  • get_query_plan: Get the query plan for a SQL query

  • get_execution_plan: Get the actual execution plan with runtime statistics for a SQL query

• Resources

  • Built-in Resources

    • adbmysql:///databases: Get all the databases in the analytic for mysql cluster

  • Resource Templates

    • adbmysql:///{schema}/tables: Get all the tables in a specific database

    • adbmysql:///{database}/{table}/ddl: Get the DDL script of a table in a specific database

    • adbmysql:///{config}/{key}/value: Get the value for a config key in the cluster

• Prompts

Not provided at the present moment.