home / mcp / teradata mcp server

Teradata MCP Server

This read-only MCP Server allows you to connect to Teradata data from Claude Desktop through CData JDBC Drivers. For full CRUD support, check out our MCP Server for Teradata (https://www.cdata.com/drivers/teradata/download/mcp).

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "cdatasoftware-teradata-mcp-server-by-cdata": {
      "command": "java",
      "args": [
        "-jar",
        "/PATH/TO/CDataMCP-jar-with-dependencies.jar",
        "/PATH/TO/Salesforce.prp"
      ]
    }
  }
}

You can query live Teradata data through a read-only MCP server that wraps the CData JDBC Driver for Teradata. This enables natural language questions to retrieve current data without writing SQL, while keeping data access controlled and read-only.

How to use

After you have the MCP server running, you use your MCP client (such as Claude Desktop or another compatible client) to connect to the local or remote MCP server. You will issue questions in natural language and the client will translate them into read-only queries against Teradata. Typical usage includes asking about metrics, summaries, or relationships across tables, such as opportunities, accounts, or events, without ever writing SQL yourself.

How to install

Prerequisites: install Java and a Java build tool (Maven) on your machine.

Steps you will perform in order:

1. Build the MCP server package.

Additional setup notes

The server is designed to be run locally on the same machine as your MCP client because it uses stdio for communication. You will run the MCP server with a Java command that points to the packaged JAR and the Teradata properties file.

Troubleshooting

If the MCP server does not appear in your client, fully quit the client and start it again. Double-check that the Teradata connection properties are correct and test the JDBC connection. If problems persist, review the license status of the CData JDBC Driver and ensure the OAuth flow (if used) can complete in your browser.

Available tools

teradata_get_tables

Retrieves a list of tables available in the Teradata data source. The output is in CSV format, with headers on the first line.

teradata_get_columns

Retrieves a list of columns for a specific table. The output is in CSV format, with headers on the first line.

teradata_run_query

Executes a SQL SELECT query against the Teradata data source and returns the results.