Teradata MCP Server

Teradata databases queried and analyzed through AI agents using direct integration.

Data last scanned yesterday · Reviewed last month

4026 tools★ 53PythonMIT

Overview

This server bridges AI agents with Teradata databases, allowing users to query, profile, and visualize data without needing manual SQL construction. It supports a range of tasks, from data engineering and exploratory analysis to monitoring capacity and automating backups via specific toolsets.

Our verdict

With a security score of 40/100, this server is classified as high-risk. This rating reflects the fact that it is a community-maintained project rather than an official vendor release, and key security aspects like authentication and read-only mode support remain unreviewed. It is suitable for experimental environments or non-sensitive data, but caution is advised for users requiring guaranteed enterprise-grade security controls.

Zero direct dependencies minimize supply-chain surface area.
Active development with commits within the last week.
Comprehensive documentation covering multiple client integration paths.
Large contributor base of 24 individuals.

Community-maintained rather than official vendor software.
Authentication methods have not yet been editorially reviewed.
Read-only execution modes are currently unverified.

Tools

Tool	Description	Risk
base_readQuery	runs a read query	low
base_tableDDL	returns the show table results	low
base_databaseList	returns a list of all databases	low
base_tableList	returns a list of tables in a database	low
base_columnDescription	returns description of columns in a table	low
base_tablePreview	returns column information and 5 rows from the table	low
base_tableAffinity	gets tables commonly used together	low
base_tableUsage	Measure the usage of a table and views by users in a given schema	low
dba_userSqlList	returns a list of recently executed SQL for a user	low
dba_tableSqlList	returns a list of recently executed SQL for a table	low

Compatibility

Client	Local	Docker	Remote	Read-only
Claude Desktop
Cursor
VS Code
Windsurf
ChatGPT

Frequently asked questions

›What are the core prerequisites to run the Teradata MCP Server?

You must have a Teradata database instance, such as the ClearScape Analytics free sandbox, and the uv package manager installed.

›How do I configure the connection to my Teradata database?

You configure the connection by setting the DATABASE_URI environment variable in your client configuration using the format teradata://<USERNAME>:<PASSWORD>@<HOST_URL>:1025/<USERNAME>.

›Does the server provide features to prevent LLM token overflow?

Yes, the server includes row limit protection with configurable DEFAULT_ROW_LIMIT and MAX_ROW_LIMIT settings.

›Can I implement custom monitoring or security auditing?

Yes, you can use the Hooks capability to intercept tool calls for custom monitoring, audit trails, or rate-limiting.

›What deployment options are available for the server?

The server can be deployed as a CLI tool using uv, as an HTTP server, within a Docker container, or as a cloud service.