Teradata

v1.0.0Databasesstable

Enables AI agents and users to query, analyze, and manage Teradata databases through modular tools for search, data quality, administration, and data science operations. Provides comprehensive database interaction capabilities including RAG applicati

teradata-mcp-servermcpai-integration
Share:
51
Stars
0
Downloads
0
Weekly
0/5

What is Teradata?

Teradata is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to enables ai agents and users to query, analyze, and manage teradata databases through modular tools for search, data quality, administration, and data science operations. provides comprehensive databas...

Enables AI agents and users to query, analyze, and manage Teradata databases through modular tools for search, data quality, administration, and data science operations. Provides comprehensive database interaction capabilities including RAG applicati

This server falls under the Databases category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • Enables AI agents and users to query, analyze, and manage Te

Use Cases

Query, analyze, and manage Teradata databases with tools for data quality and science operations. Support RAG applications.
Teradata

Maintainer

LicenseMIT License
Languagepython
Versionv1.0.0
UpdatedMay 19, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

Manual Installation

npx teradata-mcp-server

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use Teradata

The Teradata MCP Server enables AI agents and users to query, analyse, and manage Teradata databases through a rich set of modular tools covering search, data quality, administration, and data science operations including vector stores and ML functions. It provides comprehensive database interaction — from browsing schemas and running ad-hoc SQL to executing data quality checks and managing RAG (Retrieval-Augmented Generation) pipelines — all through natural language via an MCP-compatible client. Built by Teradata's own team and packaged for `uv`, it connects in under five minutes and exposes a consistent interface whether you are a DBA, data scientist, or analyst.

Prerequisites

  • Python 3.10+ and the `uv` package manager (brew install uv on macOS, pip install uv on other platforms)
  • A running Teradata database with a hostname, port 1025, username, and password
  • Network connectivity from your machine to the Teradata host on port 1025
  • Claude Desktop or another MCP-compatible AI client
  • Sufficient database permissions for the operations you intend to perform (read-only for queries, admin role for DBA tools)
1

Install the uv package manager

The server is distributed via PyPI and best run with `uv` for fast, isolated package management. Install it before proceeding.

# macOS
brew install uv

# Windows / Linux
pip install uv
2

Verify the server package is available

Run the server once with `uvx` to trigger a package download and confirm it starts without errors. Press Ctrl+C to stop.

uvx teradata-mcp-server
3

Build your DATABASE_URI

The server requires a single DATABASE_URI environment variable. Construct it from your Teradata credentials using the standard format.

# Format
teradata://<USERNAME>:<PASSWORD>@<HOST>:1025/<DATABASE>

# Example
teradata://analyst:[email protected]:1025/analytics_db
4

Configure Claude Desktop

Open Settings > Developer > Edit Config in Claude Desktop and add the Teradata server block. Set the DATABASE_URI to your actual connection string.

{
  "mcpServers": {
    "teradata-mcp-server": {
      "command": "uvx",
      "args": ["teradata-mcp-server"],
      "env": {
        "DATABASE_URI": "teradata://analyst:[email protected]:1025/analytics_db"
      }
    }
  }
}
5

Restart Claude Desktop and explore tools

Fully quit and relaunch Claude Desktop. Open a new conversation and verify the Teradata tools are listed in the tools panel — you should see tools grouped across Query, Search, Table, Data Quality, DBA, and Data Scientist categories.

6

Run a data quality check

Test the integration by asking Claude to perform a data quality analysis on a table you know exists in the database.

Teradata Examples

Client configuration

Complete claude_desktop_config.json block for the Teradata MCP Server using uvx.

{
  "mcpServers": {
    "teradata-mcp-server": {
      "command": "uvx",
      "args": ["teradata-mcp-server"],
      "env": {
        "DATABASE_URI": "teradata://myuser:[email protected]:1025/mydb"
      }
    }
  }
}

Prompts to try

Example queries covering the full range of Teradata MCP Server capabilities.

- "List all tables in the analytics schema and show their row counts."
- "Run a data quality report on the customer_master table — identify nulls, duplicates, and outliers."
- "Create a vector store from the product_descriptions column so I can run semantic search queries."
- "Who are the current database users and what are their access privileges?"
- "Find all tables related to 'sales' using semantic search across the schema."
- "Run the backup status check using the BAR tools and summarise the last 7 days of backup jobs."

Troubleshooting Teradata

Server starts but immediately exits with a connection error

Verify the DATABASE_URI format is exactly 'teradata://user:pass@host:1025/database' — the port 1025 and the protocol prefix are both required. Test network connectivity with 'telnet <host> 1025' or a Teradata client before debugging the MCP config.

DBA tools return permission denied errors

The Teradata user in your DATABASE_URI needs appropriate database permissions. For DBA tools, the user typically needs SYSADMIN or equivalent role. Use a read-only user for query-only access and a privileged user when administrative tools are needed.

Claude Desktop shows no Teradata tools after configuration

Validate the JSON syntax in claude_desktop_config.json using a JSON linter. Fully quit Claude (not just close the window) via the system tray or Activity Monitor, then relaunch. Check Claude's developer console for startup errors from uvx.

Frequently Asked Questions about Teradata

What is Teradata?

Teradata is a Model Context Protocol (MCP) server that enables ai agents and users to query, analyze, and manage teradata databases through modular tools for search, data quality, administration, and data science operations. provides comprehensive database interaction capabilities including rag applicati It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Teradata?

Follow the installation instructions on the Teradata GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with Teradata?

Teradata works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is Teradata free to use?

Yes, Teradata is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.

Browse More Databases MCP Servers

Explore all databases servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "teradata-mcp-server": { "command": "npx", "args": ["-y", "teradata-mcp-server"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use Teradata?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides