Teradata

What is mcp-teradata?

mcp-teradata is a Model Context Protocol (MCP) server specifically designed to connect Large Language Models (LLMs) with Teradata databases. It provides a set of tools that allow LLMs to perform various operations on Teradata databases, including executing SQL queries, listing database objects, and performing data analysis.

How to use mcp-teradata?

mcp-teradata can be used in two primary ways: with Claude Desktop or as an API container.

Usage with Claude Desktop

To integrate with Claude Desktop, you need to add the server configuration to your claude_desktop_config.json file. This involves specifying the command to run the server using uv and setting the DATABASE_URI environment variable to connect to your Teradata instance.

Usage as API container

For containerized deployment, you can use Docker Compose. After editing the docker-compose.yml file to update environment variables, you can build and run the containers using docker compose build and docker compose up.

Key Features of mcp-teradata

mcp-teradata offers a range of tools categorized into Query Tools, Schema Tools, and Analysis Tools:

Query Tools

• query: Executes SELECT SQL queries to retrieve data from the database, returning results as an array of objects.

Schema Tools

• list_db: Lists all databases available in the Teradata system.
• list_objects: Lists objects within a specified database.
• show_tables: Provides detailed information about tables in a database, including column names and data types.

Analysis Tools

• list_missing_values: Identifies and lists the top features with missing values in a given table.
• list_negative_values: Counts and lists features that contain negative values in a table.
• list_distinct_values: Determines and lists the number of distinct categories for a specified column in a table.
• standard_deviation: Calculates and returns the mean and standard deviation for a column in a table.

Use Cases of mcp-teradata

• Data Interaction for LLMs: Enables LLMs to directly query and retrieve data from Teradata databases.
• Business Intelligence: Facilitates LLM-driven analysis of business data stored in Teradata.
• Automated Data Exploration: Allows LLMs to explore database schemas and identify data characteristics like missing or negative values.
• Integration with AI Applications: Provides a backend for AI applications requiring programmatic access to Teradata data.

FAQ from mcp-teradata

Q: What is an MCP server? A: An MCP (Model Context Protocol) server is an implementation that allows AI models, such as LLMs, to interact with external systems and data sources, in this case, Teradata databases.

Q: What license is mcp-teradata released under? A: mcp-teradata is licensed under the MIT License, which permits free use, modification, and distribution of the software under specified terms and conditions.

Teradata MCP Server

Overview

A Model Context Protocol (MCP) server implementation that provides database interaction and business intelligence capabilities through Teradata. This server enables running SQL queries, analyzing business data

Components

Tools

The server offers six core tools:

Query Tools

• query
  • Execute SELECT queries to read data from the database
  • Input:
    • query (string): The SELECT SQL query to execute
  • Returns: Query results as array of objects

Schema Tools

• list_db

  • Lists all databases in the Teradata system
  • Returns: List of databases

• list_objects

  • Lists objects in a database
  • Input:
    • db_name (string): Database name
  • Returns: List of database objects under provided or user defaul database

• show_tables

  • Show detailed information about a database tables
  • Input:
  • table_name (string): Name of the table
  • Returns: Array of column names and data types

Analysis Tools

• list_missing_values
  • Lists the top features with missing values in a table
• list_negative_values
  • Lists how many features have negative values in a table
• list_distinct_values
  • Lists how many distinct categories are there for column in the table
• standard_deviation
  • What is the mean and standard deviation for column in table?

Usage with Claude Desktop

uv

# Add the server to your claude_desktop_config.json
{
  "mcpServers": {
    "teradata": {
      "command": "uv",
      "args": [
        "--directory",
        "/Users/MCP/mcp-teradata",
        "run",
        "teradata-mcp"
      ],
      "env": {
        "DATABASE_URI": "teradata://user:passwd@host"
      }
    }
  }
}

Usage as API container

Make sure to edit docker-compose.yml and update environment variable

docker compose build
docker compose up

Building

UV:

uv build

License

This MCP server is licensed under the MIT License. This means you are free to use, modify, and distribute the software, subject to the terms and conditions of the MIT License. For more details, please see the LICENSE file in the project repository.