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.

We are providing groupings of tools and associated helpful prompts

• Base tools, prompts and resources to interact with your Teradata platform:
  • Base Tools
• DBA tools, prompts and resources to facilitate your platform administration tasks:
  • DBA Tools
• Data Quality tools, prompts and resources accelerate exploratory data analysis:
  • Data Quality Tools
• Security tools, prompts and resources to resolve permissions:
  • Security Tools
• Feature Store tools, prompts and resources to manage the Enterprise Feature Store:
  • Feature Store Tools
• RAG tools, prompts and resources to manage vector store creation and use
  • RAG Tools
• Custom Semantic Layer to easily implement domain-specific tools, prompts and resources based on your business data. Refer to semantic layer definition

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 conect to, then leverage Teradata Clearscape Experience

Step 2. - To cofigure and run the MCP server, refer to the Getting stated guide.

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

If you want to quickly evaluate the tool, we recommend using Claude desktop, the uv package manager and Teradata Clearscape Experience.

1. Get your Teradata database credentials or create a free sandbox at Teradata Clearscape Experience.
2. Install uv. If you are on macOS, use Homebrew: brew install uv
3. Clone this repository with git clone https://github.com/Teradata/teradata-mcp-server.git
4. Install Claude Desktop
5. Configure the claude_desktop_config.json (Settings>Developer>Edit Config) by adding the code below, updating the PATH_TO_DIRECTORY (where you cloned the repo in step 2) and database username, password and URL.

{
  "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>"
      }
    }
  }