Teradata MCP Server

Overview

The Teradata MCP server provides sets of tools and prompts, grouped as modules for interacting with Teradata databases. Enabling AI agents and users to query, analyze, and manage their data efficiently.

Key features

Available tools and prompts

We are providing groupings of tools and associated helpful prompts to support all type of agentic applications on the data platform.

• Search tools, prompts and resources to search and manage vector stores.
  • RAG Tools rapidly build RAG applications.
• Query tools, prompts and resources to query and navigate your Teradata platform:
  • Base Tools
• Table tools, to efficiently and predictably access structured data models:
  • Feature Store Tools to access and manage the Teradata Enterprise Feature Store.
  • Semantic layer definitions to easily implement domain-specific tools, prompts and resources for your own business data models.
• Data Quality tools, prompts and resources accelerate exploratory data analysis:
  • Data Quality Tools
• DBA tools, prompts and resources to facilitate your platform administration tasks:
  • DBA Tools
  • Security Tools

Getting Started

Step 1. - Identify the running Teradata System, you need username, password and host details to populate "teradata://username:password@host:1025". If you do not have a Teradata system to connect to, then leverage Teradata Clearscape Experience

Step 2. - To configure and run the MCP server, refer to the Getting started guide.

Step 3. - There are many client options available, the Client Guide explains how to configure and run a sample of different clients.

A Video Library has been curated to assist.

Quick start with Claude Desktop (no installation)

Claude Desktop can get and start the Teradata MCP server in the background using uv. No permanent installation needed.

Pre-requisites

1. Get your Teradata database credentials or create a free sandbox at Teradata Clearscape Experience.
2. Install Claude Desktop.
3. Install uv. If you are on MacOS, Use Homebrew: brew install uv.

Configure the claude_desktop_config.json (Settings>Developer>Edit Config) by adding the configuration below, updating the database username, password and URL:

{
  "mcpServers": {
    "teradata": {
      "command": "uvx",
      "args": ["teradata-mcp-server", "--profile", "all"],
      "env": {
        "DATABASE_URI": "teradata://<USERNAME>:<PASSWORD>@<HOST_URL>:1025/<USERNAME>"
      }
    }
  }
}

CLI Installation

We recommend uv or pipx to install teradata-mcp-server as a CLI tool on your system. They provide isolated environments and ensure the teradata-mcp-server command is available system-wide without interfering with system Python.

uv tool install "teradata-mcp-server"

or with pipx

pipx install "teradata-mcp-server"

To install the optional Enterprise Feature Store (fs) and Enterprise Vector Store (evs) packages:

uv tool install "teradata-mcp-server[fs,evs]"

Alternatively, you may use pip in a virtual environment (Python>=3.11):

pip install teradata-mcp-server

Build from Source (Development)

For development or customization, you can build from source:

1. Install uv. If you are on macOS, use Homebrew: brew install uv
2. Clone this repository: git clone https://github.com/Teradata/teradata-mcp-server.git
3. Navigate to the directory: cd teradata-mcp-server
4. Run the server: uv run teradata-mcp-server

For Claude Desktop with development build, use this configuration:

{
  "mcpServers": {
    "teradata": {
      "command": "uv",
      "args": [
        "--directory",
        "<PATH_TO_DIRECTORY>/teradata-mcp-server",
        "run",
        "teradata-mcp-server"
      ],
      "env": {
        "DATABASE_URI": "teradata://<USERNAME>:<PASSWORD>@<HOST_URL>:1025/<USERNAME>",
        "MCP_TRANSPORT": "stdio"
      }
    }
  }
}

Contributing

Please refer to the Contributing guide and the Developer Guide.

---

Certification