TiDB Database Connector MCP Server

DatabasesPython

Connect to and query TiDB databases directly from your AI assistant

Available Tools

execute_query

Execute a SQL query against the TiDB database and return the results

show_tables

List all tables in the connected TiDB database

describe_table

Show the schema of a specific table in the database

TiDB Database Connector provides a seamless interface between AI assistants and TiDB databases. It allows you to execute SQL queries, manage database schemas, and analyze data directly through natural language conversations. This MCP server implementation specifically targets TiDB Cloud's serverless database offerings, enabling powerful database interactions without leaving your AI assistant interface.

Overview

TiDB Database Connector enables AI assistants to interact directly with TiDB databases. This allows you to perform database operations, run SQL queries, and analyze data through natural language conversations with your AI assistant.

Prerequisites

Before installing the TiDB Database Connector, you'll need:

Python and the uv package installer
A TiDB Cloud account with a database cluster (you can create a free tier account at tidbcloud.com)
Your TiDB connection credentials (host, port, username, password)

Installation

Clone the repository:

git clone https://github.com/c4pt0r/mcp-server-tidb
cd mcp-server-tidb

Install the package and dependencies using uv:
```
uv venv
uv pip install -e .
```

Create a .env file in the project directory based on the .env.example file with your TiDB connection details:

TIDB_HOST=gateway01.us-east-1.prod.aws.tidbcloud.com
TIDB_PORT=4000
TIDB_USERNAME=xxxxxxxxxx.<username>
TIDB_PASSWORD=your_password
TIDB_DATABASE=test

Configuration for Claude Desktop

To use the TiDB Database Connector with Claude Desktop:

Create or update your claude_desktop_config.json file:

{
  "mcpServers": {
    "tidb": {
      "command": "uv",
      "args": [
        "--directory",
        "/path/to/mcp-server-tidb",
        "run",
        "src/main.py"
      ]
    }
  }
}

If you're using WSL, your configuration should look like:

{
  "mcpServers": {
    "tidb": {
      "command": "wsl.exe",
      "args": [
        "bash",
        "-c",
        "/path/to/uv --directory /path/to/mcp-server-tidb run python src/main.py"
      ]
    }
  }
}

Replace /path/to/mcp-server-tidb with the actual path to your cloned repository.
Restart Claude Desktop to apply the changes.

Usage

Once configured, you can interact with your TiDB database through natural language. For example:

"Show me all tables in the database"
"Run a query to find all users who signed up in the last month"
"Create a new table for storing product information"
"Analyze the sales data by region"

The connector will translate your requests into SQL queries, execute them against your TiDB database, and return the results.