Frequently Asked Questions (FAQ) - Treasure Data MCP Server

Q: What is the Treasure Data MCP Server? A: The Treasure Data MCP Server is a Model Context Protocol (MCP) server that enables AI models like Claude Code and Claude Desktop to interact with the Treasure Data API. It allows AI Agents to programmatically manage databases and workflows within Treasure Data.

Q: Is the Treasure Data MCP Server officially supported by Treasure Data Inc.? A: No, this is a personal development project and is not officially affiliated with or endorsed by Treasure Data Inc. Use it at your own risk.

Q: What are the key features of the Treasure Data MCP Server? A: Key features include database management (listing and retrieving databases and tables) and workflow project management (listing, retrieving, and downloading projects, listing files within archives, and reading specific files).

Q: What is MCP (Model Context Protocol)? A: MCP is an open protocol that standardizes how applications provide context to Large Language Models (LLMs).

Q: How do I authenticate with the Treasure Data MCP Server? A: You need to provide a Treasure Data API key via the TD_API_KEY environment variable. You can also specify the Treasure Data endpoint using the TD_ENDPOINT environment variable (defaults to api.treasuredata.com).

Q: What are the software requirements for running the Treasure Data MCP Server? A: The project requires Python 3.11+ and the following packages: requests, pydantic, and mcp. You can install the dependencies using pip install -r requirements.txt or uv pip install -e ..

Q: How do I set up the Treasure Data MCP Server with Claude Code? A: 1. Clone the repository. 2. Add the MCP server using the Claude Code CLI, specifying the absolute path to the server.py file and setting the necessary environment variables.

Q: How do I set up the Treasure Data MCP Server with Claude Desktop? A: Configure the MCP server in your claude_desktop_config.json file, specifying the command, arguments, and environment variables needed to run the server.

Q: What can I do with the downloaded project archives? A: You can examine the detailed project contents, including SQL queries and workflow definitions, to understand and optimize your Treasure Data workflows.

Q: How does the Treasure Data MCP Server integrate with the UBOS platform? A: The UBOS platform provides a centralized environment for managing AI Agent components, simplifies deployment, offers a secure environment, ensures scalability and reliability, and enables multi-agent orchestration.

Q: Where can I find the Treasure Data MCP Server in UBOS? A: The Treasure Data MCP Server is available on the UBOS Asset Marketplace.

Q: What are some example use cases for the Treasure Data MCP Server? A: Use cases include automated data auditing, intelligent workflow orchestration, automated data pipeline management, proactive data governance, and custom AI-powered data analysis.

Q: What versions of Python are supported? A: Python 3.11 and later are supported.

Q: What if I encounter issues or have questions about the Treasure Data MCP Server? A: Since this is a personal project, support may be limited. However, you can review the project’s documentation and code on GitHub for guidance. You can also consult the UBOS community forums for assistance.