Teradata MCP Server

What does “Teradata” MCP Server do?

The Teradata MCP (Model Context Protocol) Server is designed to provide seamless integration between AI assistants and Teradata databases, empowering advanced database interaction and business intelligence workflows. It enables AI-driven systems to execute SQL queries, explore database schemas, and perform analytical operations directly on Teradata data warehouses. By exposing tools for querying, schema inspection, and data analysis, Teradata MCP Server allows developers and AI agents to automate tasks such as retrieving business insights, managing large datasets, and enhancing data-driven application development. Its functionality supports improved productivity for data analysts, engineers, and AI systems requiring real-time access to enterprise data stored in Teradata.

List of Prompts

No prompt templates are explicitly mentioned in the repository.

List of Resources

No resources are explicitly documented in the repository.

List of 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.

• 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 the provided or user default database.

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

• 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 there are for a column in the table.

• standard_deviation
  Returns the mean and standard deviation for a column in a table.

Use Cases of this MCP Server

• Database Query Automation
  Leverage the query tool to automate retrieval of business data, enabling AI agents or developers to perform complex SELECT operations without manual SQL scripting.

• Schema Exploration
  Use list_db, list_objects, and show_tables to understand database structure, discover available tables, and inspect column types—essential for onboarding new datasets or building data-driven applications.

• Data Quality Analysis
  Employ list_missing_values and list_negative_values to detect data quality issues, such as missing or erroneous entries, which is crucial for data preprocessing and analytics.

• Categorical Data Insights
  Utilize list_distinct_values to identify unique categories within columns, supporting feature engineering and business reporting.

• Statistical Summaries
  The standard_deviation tool enables quick access to key statistics (mean and standard deviation), aiding in descriptive analytics and anomaly detection.

How to set it up

Windsurf

No specific setup instructions provided.

Claude

1. Ensure you have uv installed as a prerequisite.
2. Clone or download the mcp-teradata repository.
3. Locate your claude_desktop_config.json configuration file.
4. Add the Teradata MCP Server configuration under the mcpServers object:

   {
     "mcpServers": {
       "teradata": {
         "command": "uv",
         "args": [
           "--directory",
           "/Users/MCP/mcp-teradata",
           "run",
           "teradata-mcp"
         ],
         "env": {
           "DATABASE_URI": "teradata://user:passwd@host"
         }
       }
     }
   }
   

5. Save the configuration file and restart Claude Desktop.
6. Verify the connection by running a test query or checking logs.

Securing API Keys

Store sensitive information (like DATABASE_URI) in the env section:

"env": {
  "DATABASE_URI": "teradata://user:passwd@host"
}

Use environment variables or a secrets manager as needed.

Cursor

No specific setup instructions provided.

Cline

No specific setup instructions provided.

How to use this MCP inside flows

Using MCP in FlowHunt

To integrate MCP servers into your FlowHunt workflow, start by adding the MCP component to your flow and connecting it to your AI agent:

Click on the MCP component to open the configuration panel. In the system MCP configuration section, insert your MCP server details using this JSON format:

{
  "teradata": {
    "transport": "streamable_http",
    "url": "https://yourmcpserver.example/pathtothemcp/url"
  }
}

Once configured, the AI agent is now able to use this MCP as a tool with access to all its functions and capabilities. Remember to change "teradata" to whatever the actual name of your MCP server is and replace the URL with your own MCP server URL.

Overview

Roots support: Not documented

Based on the available documentation and feature set, the Teradata MCP Server delivers solid database tooling but lacks comprehensive documentation on resources, prompt templates, Roots, and sampling support. It is functionally rich for database tasks but limited in standard MCP features and guidance.

MCP Score

Rating:
I would rate this MCP server a 5 out of 10. It provides a robust set of database tools and clear licensing, but lacks documentation for prompt templates, resources, Roots, and sampling, as well as platform-agnostic setup instructions. It is suitable for technical users already familiar with Teradata and MCP concepts.