freshcrate
Skin:/
Home > MCP Servers > teradata-mcp-server

teradata-mcp-server

The community development of a MCP server for a Teradata database

Why this rank:Strong adoptionRecent releaseHealthy release cadence

Description

The community development of a MCP server for a Teradata database

README

CI/CD

GitHub Actions Workflow

The CI workflow (.github/workflows/ci.yml) runs on every push to main and on pull requests targeting main. It consists of three parallel jobs:

Jobs

Job What it does
Lint Runs ruff check and ruff format --check against src/
Type Check Runs mypy against src/ (installs the dev extra for type stubs)
Integration Tests Runs the test suite against a live Teradata database

All jobs use uv sync --frozen to ensure the lock file is up to date — if uv.lock is stale relative to pyproject.toml, the job will fail.

Running Checks Locally

# Lint
uv run ruff check src/
uv run ruff format --check src/

# Type check
uv sync --extra dev
uv run mypy src/

# Integration tests (requires a live Teradata connection)
export DATABASE_URI="teradata://user:pass@host:1025/database"
uv run python tests/run_mcp_tests.py "uv run teradata-mcp-server"

Configuring the DATABASE_URI Secret

The integration test job requires a DATABASE_URI repository secret to connect to a Teradata instance. Without it, the test job logs a warning and skips.

To configure:

  1. Go to Settings > Secrets and variables > Actions in the GitHub repository
  2. Click New repository secret
  3. Name: DATABASE_URI
  4. Value: a Teradata connection URI, e.g. teradata://user:pass@host:1025/database

You need to be on the Teradata VPN to access the test database, so this secret should only be added by authorized Teradata personnel. If you don't have access, the tests will simply be skipped.

The test job is automatically skipped on fork PRs (where secrets are unavailable) to avoid failures.

Concurrency

The workflow uses concurrency groups scoped to the branch/PR ref. If a new commit is pushed while a previous run is still in progress, the older run is cancelled to save CI minutes and avoid database contention.

Release History

VersionChangesUrgencyDate
v0.2.3## What's Changed * fixed profile `run` section by @remi-td in https://github.com/Teradata/teradata-mcp-server/pull/311 * Update td_connect.py by @NathanG-TD in https://github.com/Teradata/teradata-mcp-server/pull/312 * feat: automated GitHub Actions release workflow for PyPI publishing by @dtehan-td in https://github.com/Teradata/teradata-mcp-server/pull/314 * fix: add setup-uv to publish jobs so uvx is available by @dtehan-td in https://github.com/Teradata/teradata-mcp-server/pull/315 **FullHigh5/19/2026
v0.2.2## v0.2.2 Release Notes ### New Features - **Hooks support** (#306) — Users can now plug in custom logic around tool calls. Pre- and post-call hooks allow integration with logging, validation, or transformation workflows without modifying the server. - **Lineage and dependency graph analysis** (#302) — New tools for analysing Teradata object lineage and generating dependency graphs across tables, views, and procedures. - **`base_columnDescription` tool** (#301) — New tool returning humanHigh5/15/2026
v0.2.1## What's Changed * Issue 271 & security dependencies by @dtehan-td in https://github.com/Teradata/teradata-mcp-server/pull/290 **Full Changelog**: https://github.com/Teradata/teradata-mcp-server/compare/0.2.0...v0.2.1High4/9/2026
0.2.0## What's Changed * Fix for #232 tools missing descriptions by @dtehan-td in https://github.com/Teradata/teradata-mcp-server/pull/233 * Feature: BAR Tools Implementation by @Asimz4321 in https://github.com/Teradata/teradata-mcp-server/pull/187 * Custom tools docs and defaults by @remi-td in https://github.com/Teradata/teradata-mcp-server/pull/234 * Tool parameters by @remi-td in https://github.com/Teradata/teradata-mcp-server/pull/238 * Updated Link to the Trusted Data Agent by @rgeissen Medium3/24/2026
v0.1.6## Key updates * Added Teradata Vector Store tools (tdvs) * Added plotting tools (plot) * Added Teradata machine learning tools (tdml) * Default configs (profiles) embedded in build * Tool descriptions display in all clients * Prompts refinement * Other bug fixes ## What's Changed * Docs/restructure and fix fstrings by @remi-td in https://github.com/Teradata/teradata-mcp-server/pull/178 * removed profile condition from claude quickstart by @remi-td in https://github.com/Teradata/teraLow11/6/2025
0.1.5.post2## What's Changed * Embed config files in the build * Removed profile condition from claude quickstart * Windows cli fix * Docs restructure and update **Full Changelog**: https://github.com/Teradata/teradata-mcp-server/compare/v0.1.4...v0.1.5Low9/13/2025
v0.1.4## Key updates * Implemented end-user authentication and session contexts * Upgraded to FastMCP 2.0 * Revised documentation * Enhanced custom tools & prompts features and bug fixes ## What's Changed * type_hint working as part of description by @rgeissen in https://github.com/Teradata/teradata-mcp-server/pull/131 * Updated documentation and requirements for client tools in the examples by @dtehan-td in https://github.com/Teradata/teradata-mcp-server/pull/133 * linting the code base, fiLow9/11/2025
v0.1.1## What's Changed * Simplifies dependencies and reduced build size, made some modules optional * MCP Tool Fixes: dba_flowControl, dba_featureUsage, dba_userDelay, etc.. * Added automated and LLM-independent tool testing framework * Allow parameters definition in prompt declarations * New Prompt Definition Guidelines **Full Changelog**: https://github.com/Teradata/teradata-mcp-server/compare/v0.1.0...v0.1.1Low8/13/2025
v0.1.0First pre-release of Teradata MCP Server, Community Edition. Features: - Initial set of tools and prompts for building agentic applications on Teradata. - Modules: Search, Query, Table, Data Quality, DBA, Security, Semantic Layer. - Documentation, quick start guides, and examples included. Notes: - This is a pre-1.0 version. Interfaces and APIs may change.Low8/11/2025

Dependencies & License Audit

Loading dependencies...

Similar Packages

AI-Skills🤖 Enhance AI capabilities with modular Skills that provide expert knowledge, workflows, and integrations for any project.main@2026-06-07
telegram-mcp🤖 Manage multiple Telegram accounts effortlessly with AI-driven tools for bulk messaging, scheduling, and more in one easy-to-use platform.main@2026-06-07
Enterprise-Multi-AI-Agent-Systems-🤖 Build and deploy scalable Multi-AI Agent systems with LangGraph and Groq LLMs to enhance intelligence across enterprise applications.main@2026-06-07
AIDomesticCoreAIJđŸ› ī¸ Build a robust AI Kernel for stable, auditable, and sovereign AI systems, ensuring secure execution and compliance across various domains.main@2026-06-07
argus-mcp🔍 Enhance code quality with Argus MCP, an AI-driven code review server using a Zero-Trust model for safe and efficient development.main@2026-06-07

More in MCP Servers

claude-plugins-officialOfficial, Anthropic-managed directory of high quality Claude Code Plugins.
langchain4jLangChain4j is an open-source Java library that simplifies the integration of LLMs into Java applications through a unified API, providing access to popular LLMs and vector databases. It makes impleme
hyperframesWrite HTML. Render video. Built for agents.
claude-code-guideClaude Code Guide - Setup, Commands, workflows, agents, skills & tips-n-tricks go from beginner to power user!