About mcp-server-tidb
mcp-server-tidb is a Python MCP server for TiDB serverless databases, installed with uv. It is aimed at users who want to reach a TiDB database from clients such as Claude Desktop.
Key features
- 01Connects to TiDB serverless database clusters
- 02Configuration through environment variables or a .env file
- 03Local installation and run with uv
- 04Claude Desktop setup examples, including WSL
Use cases
- 01Querying a TiDB database from Claude Desktop
- 02Connecting to TiDB from a WSL environment
MCP support
Runs as an MCP server that clients such as Claude Desktop launch through claude_desktop_config.json. The README does not specify which tools or resources it exposes.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEmcp-server-tidb
MCP server implementation for TiDB (serverless) database.
Prerequisites
- uv (Python package installer)
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 .
Configuration
Go tidbcloud.com to create a free TiDB database cluster
Configuration can be provided through environment variables, or using .env:
TIDB_HOST- TiDB host address, e.g. 'gateway01.us-east-1.prod.aws.tidbcloud.com'TIDB_PORT- TiDB port (default: 4000)TIDB_USERNAME- Database username, e.g. 'xxxxxxxxxx.<username>'TIDB_PASSWORD- Database passwordTIDB_DATABASE- Database name, default is test
Run with Claude Desktop
Config Claude Desktop, HOWTO
claude_desktop_config.json:
{
"mcpServers": {
"tidb": {
"command": "uv",
"args": [
"--directory",
"/path/to/mcp-server-tidb",
"run",
"src/main.py"
]
}
}
}
If you're running mcp-server-tidb in WSL, the claude_desktop_config.json should look like this:
{
"mcpServers": {
"tool-with-env-vars": {
"command": "wsl.exe",
"args": [
"bash",
"-c",
"/path/to/uv --directory /path/to/mcp-server-tidb run python src/main.py"
]
}
}
}
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.