---
title: "Teradata MCP Server: review, setup & limitations · Undominated.ai"
canonical: https://undominated.ai/mcp-servers/teradata/
description: "Explore Teradata tables, profile data and investigate workloads using selectable tool modules."
---

# Teradata MCP Server: review, setup & limitations · Undominated.ai

> Explore Teradata tables, profile data and investigate workloads using selectable tool modules.

[← Explore all mcp servers](/mcp-servers/)

ANALYTICS DATABASES / Teradata

# Teradata MCP Server

Explore Teradata tables, profile data and investigate workloads using selectable tool modules.

 [See setup guidance ↓](#setup)[Original source ↗](https://github.com/Teradata/teradata-mcp-server)

SOURCE REVIEW

 Reviewed 2026-10-14
 Evidence 4 linked sources
 Publisher Teradata
 Licence [MIT ↗](https://github.com/Teradata/teradata-mcp-server/blob/0e305a51fb7e9437dcf7436b8929e9d440f32234/LICENSE)
 Revision 0e305a51fb7e
 [Read what was—and wasn’t—checked ↓](#review)

“Connect AI agents directly to Teradata with enterprise security and extensibility.”

 [Teradata · upstream description ↗](https://github.com/Teradata/teradata-mcp-server/blob/0e305a51fb7e9437dcf7436b8929e9d440f32234/README.md) Our analysis follows below.

01 / THE REASONING

## Why this made the selection.

 - Explore Teradata tables, profile data and investigate workloads using selectable tool modules.
- The setup documentation makes this operating boundary explicit: The DATABASE_URI user determines SQL and administration privileges; module selection does not replace database authorization.

### A good fit for

 - Explore Teradata tables, profile data and investigate workloads using selectable tool modules.
- With Python 3.11+ and uvx, launch teradata-mcp-server and supply DATABASE_URI for the intended Teradata account and database. Choose the documented tool modules and row caps before connecting.

### Weigh up before choosing

 - The package classifies itself Alpha; DEFAULT_ROW_LIMIT and MAX_ROW_LIMIT cap returned rows, so a response need not represent the complete table.
- Package/container parity with the pinned source and transitive dependency security were not established.

02 / THE REVIEW RECORD

## What we actually inspected.

Source review has boundaries. A clear record is more useful than a “safe” badge.

### Material inspected

 - README.md
- LICENSE
- pyproject.toml
- src/teradata_mcp_server/server.py

### Our findings

 - The DATABASE_URI user determines SQL and administration privileges; module selection does not replace database authorization.
- The package classifies itself Alpha; DEFAULT_ROW_LIMIT and MAX_ROW_LIMIT cap returned rows, so a response need not represent the complete table.

### Not established by this review

 - No server installation, authentication, live tool execution or isolation test was performed.
- Package/container parity with the pinned source and transitive dependency security were not established.

The review applies to the material and revision named here. A newer upstream release can change its behavior.

03 / PUT IT TO WORK

## Connect a server deliberately.

[Upstream setup instructions ↗](https://github.com/Teradata/teradata-mcp-server/blob/0e305a51fb7e9437dcf7436b8929e9d440f32234/docs/server_guide/INSTALLATION.md)

DOCUMENTED COMMAND

 uv tool install "teradata-mcp-server" Copy command ↗

Copying does not execute this command. It may retrieve a newer version than the reviewed source.

 - The command above is INSTALLATION.md's uv tool line. The README's Claude Desktop block runs uvx teradata-mcp-server instead, with no separate install. Neither was run.
- Set DATABASE_URI to the Teradata connection string for the target system, using an account limited to what the agent may read or change.
- Expose only the tool suites the connecting role needs via the documented customisation options; use streamable-http only behind the security patterns INSTALLATION.md points to.

### Before you start

 - A Teradata database or free ClearScape Analytics sandbox.
- Python 3.11+ with uv installed.

### Documented configuration example

Use the client and authentication context described in the setup guidance. Configuration formats vary between hosts.

 {
 "mcpServers": {
 "teradata": {
 "command": "uvx",
 "args": [
 "teradata-mcp-server"
 ],
 "env": {
 "DATABASE_URI": "teradata://<USERNAME>:<PASSWORD>@<HOST_URL>:1025/<USERNAME>"
 }
 }
 }
} Copy configuration ↗

### Compatibility

MCP clients supporting stdio; documented quick starts for Claude Desktop, VS Code Copilot and Open WebUI. · A Teradata database or free ClearScape sandbox, Python 3.11+ and uv.

### Implementation

Python

### Transports

stdio · Streamable HTTP · SSE

### Local process with service or workstation access

 - The DATABASE_URI user determines SQL and administration privileges; module selection does not replace database authorization.

### Cost model

Publisher service entitlements, API usage and infrastructure charges apply where applicable; the MCP source licence does not include external services.

04 / FOLLOW THE EVIDENCE

## The source trail.

Our notes are separate from the original resource. Check upstream before adopting a new version.

 - [Pinned publisher README and migration notices ↗](https://github.com/Teradata/teradata-mcp-server/blob/0e305a51fb7e9437dcf7436b8929e9d440f32234/README.md) Checked 2026-10-14 https://github.com/Teradata/teradata-mcp-server/blob/0e305a51fb7e9437dcf7436b8929e9d440f32234/README.md Supports: description, setup, capabilities, review, limitations
- [Licence text at the reviewed commit ↗](https://github.com/Teradata/teradata-mcp-server/blob/0e305a51fb7e9437dcf7436b8929e9d440f32234/LICENSE) Checked 2026-10-14 https://github.com/Teradata/teradata-mcp-server/blob/0e305a51fb7e9437dcf7436b8929e9d440f32234/LICENSE Supports: license
- [Pinned package metadata ↗](https://github.com/Teradata/teradata-mcp-server/blob/0e305a51fb7e9437dcf7436b8929e9d440f32234/pyproject.toml) Checked 2026-10-14 https://github.com/Teradata/teradata-mcp-server/blob/0e305a51fb7e9437dcf7436b8929e9d440f32234/pyproject.toml Supports: install, language, review
- [Pinned implementation inspected for launch or permission boundary ↗](https://github.com/Teradata/teradata-mcp-server/blob/0e305a51fb7e9437dcf7436b8929e9d440f32234/src/teradata_mcp_server/server.py) Checked 2026-10-14 https://github.com/Teradata/teradata-mcp-server/blob/0e305a51fb7e9437dcf7436b8929e9d440f32234/src/teradata_mcp_server/server.py Supports: review, install, access, limitations

KEEP COMPARING

## Other approaches to consider.

Related by category or shared topics. These are alternatives to inspect, not a measured quality order.

 [### CrateDB MCP Server ↗ Python MCP server from the crate organisation that runs SQL against a CrateDB cluster over its HTTP endpoint behind a SELECT-only check, reads table columns, table metadata and cluster health, lists a curated CrateDB documentation index, and fetches documentation pages by link under three permitted URL prefixes.](/mcp-servers/cratedb/)[### ClickHouse MCP Server ↗ Queries ClickHouse and inspects table metadata, with read-only SQL by default and separate authentication for network transports.](/mcp-servers/clickhouse/)[### Firebolt MCP Server ↗ Go MCP server from Firebolt that connects a client to Firebolt Cloud or Firebolt Core, runs SQL, and exposes Firebolt documentation tools.](/mcp-servers/firebolt/)

 [AI Tools ↗](/tools/)[Skills ↗](/skills/)[Agents ↗](/agents/)[MCP Servers ↗](/mcp-servers/)[Workflows ↗](/workflows/)

## Continue your investigation

 - [Inspect resource evidence](/tools/)
- [Choose a host](/agents/)
- [Inspect reusable workflows](/skills/)
- [Use Undominated data](/api/)
