MCP.so
Sign In

TDengine Query MCP Server

@Abeautifulsnow

Basic information

Category

Other

License

MIT

Transports

stdio

Author

Abeautifulsnow

About TDengine Query MCP Server

TDengine MCP Server.

#tdengine

TDengine Query MCP Server config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "tdengine": {
      "command": "uvx",
      "args": [
        "tdengine-mcp-server",
        "-th",
        "YOUR_TDengine_HOST",
        "-tu",
        "YOUR_TDengine_USERNAME",
        "-pwd",
        "YOUR_TDengine_PASSWORD",
        "-db",
        "YOUR_TDengine_DATABASE",
        "-ll",
        "debug",
        "-trans",
        "stdio"
      ]
    }
  }
}

TDengine Query MCP Server tools

Tool list not available yet

This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.

Fetch the live tool list by running this server in a temporary sandbox using the button above.

Overview

What is TDengine Query MCP Server?

A Model Context Protocol (MCP) server that provides read-only TDengine database queries for AI assistants. It allows users to execute queries, explore database structures, and investigate data directly from their AI-powered tools.

How to use TDengine Query MCP Server?

Install via pip install tdengine_mcp_server, uvx tdengine-mcp-server, or run directly from source with uv run src/tdengine_mcp_server. Configure connection using command-line arguments (e.g., -th <host> -db <database>) or a .env file (which takes priority). The server works with any MCP-compatible client, including Cursor IDE and Anthropic Claude.

Key features of TDengine Query MCP Server

  • Executes only read‑only SQL queries (SELECT, SHOW, DESCRIBE)
  • Returns database/stable metadata and structure info
  • Lists available databases and stables
  • Compatible with all MCP‑supporting AI assistants
  • Supports both stdio and SSE transports
  • Configurable via environment variables or CLI arguments

Use cases of TDengine Query MCP Server

  • Query the first 10 records of a database from an AI assistant
  • Analyze sales data per region for a given month
  • Inspect table schemas and metadata without writing access
  • List all available databases on a TDengine instance

Frequently asked questions

1

What SQL operations are allowed?

Only read‑only queries: SELECT, SHOW, and DESCRIBE. INSERT, UPDATE, DELETE, CREATE, ALTER, and other write operations are blocked.

2

How do I configure the connection to my TDengine instance?

Set environment variables (host, port, username, password, database, timeout) in a `.env` file, or pass them via command‑line flags like `-th`, `-tp`, `-db`, etc. The `.env` file takes precedence.

3

Which AI tools can use this MCP server?

Any tool that supports the Model Context Protocol, such as Cursor IDE, Anthropic Claude, and other MCP‑compatible assistants.

4

Is the server secure for production use?

Yes – it enforces read‑only operations, preventing accidental or malicious data modifications. Only SELECT, SHOW, and DESCRIBE statements are allowed.

5

What should I do if I get a connection error?

Verify your database credentials, ensure the TDengine server is running and accessible, check firewall rules, and set `LOG_LEVEL` to DEBUG for more details.

Comments

More Other MCP servers