Frequently Asked Questions (FAQ) about TDengine MCP Server

Q: What is an MCP Server? A: MCP (Model Context Protocol) is an open protocol standardizing how applications provide context to LLMs. An MCP server acts as a bridge, allowing AI models to access and interact with external data sources and tools, like TDengine databases.

Q: What is TDengine? A: TDengine is an open-source, high-performance time-series database (TSDB) designed for IoT, connected cars, industrial IoT, and IT infrastructure monitoring. It is designed to handle massive volumes of time-stamped data with speed and efficiency.

Q: What does the TDengine MCP Server do? A: It provides read-only access to TDengine databases for AI assistants, allowing them to execute queries, explore database structures, and investigate data. It supports SELECT, SHOW, and DESCRIBE queries.

Q: What operations are NOT supported by the TDengine MCP Server? A: The server does NOT support write operations like INSERT, UPDATE, DELETE, CREATE, or ALTER. It’s designed solely for read-only data exploration and analysis.

Q: Which AI tools are compatible with this MCP Server? A: Any tool that supports the Model Context Protocol (MCP), including Cursor IDE and Anthropic Claude, can be used. Follow the tool’s MCP configuration instructions.

Q: How do I install the TDengine MCP Server? A: You can install it by running from source code, using pip, using uvx, or from Smithery using npx.

Q: What are the configuration options for the server? A: You can configure it using environment variables in a .env file or through command-line arguments.

Q: What environment variables can I configure? A: You can configure LOG_LEVEL, TDENGINE_HOST, TDENGINE_PORT, TDENGINE_USERNAME, TDENGINE_PASSWORD, TDENGINE_DATABASE, TDENGINE_TIMEOUT, and TRANSPORT.

Q: How do I use the server with an AI assistant? A: Configure your AI assistant with the connection details of the MCP server, and then use natural language prompts to ask questions about the data or request specific queries.

Q: What are the available tools for interacting with the TDengine MCP Server? A: The server provides two main tools: query (to execute SQL queries) and info (to get detailed information about tables).

Q: Is the TDengine MCP Server secure? A: Yes, it only allows read-only queries, preventing any data modification.

Q: What do I do if I have connection issues? A: Verify your database credentials, ensure the TDengine server is running and accessible, check for firewall rules, and enable debug mode.

Q: What do I do if my query execution fails? A: Verify your SQL syntax, check that you’re only using supported query types (SELECT, SHOW, DESCRIBE), and ensure your query is truly read-only.

Q: How does the TDengine MCP Server integrate with UBOS platform? A: The TDengine MCP Server seamlessly integrates with the UBOS platform, providing a comprehensive environment for AI agent development and deployment. The UBOS platform helps to orchestrate AI Agents, connect them with your enterprise data, build custom AI Agents with your LLM model and Multi-Agent Systems.