mcpField
T
Teradata MCP Server Template

Teradata MCP Server Template

Local
github.com/TeradataDeveloper Tools58Updated 3d ago

About Teradata MCP Server Template

Teradata MCP Server is a community-developed MCP server that connects AI agents directly to Teradata databases. It targets analysts, data engineers and database administrators who need enterprise security and extensibility.

Key features

  1. 01Natural language data exploration without writing SQL
  2. 02Semantic layers and tools defined in YAML
  3. 03Hooks for monitoring, audit and rate limiting
  4. 04Configurable row limits for query results
  5. 05Response caching for repeated database queries
  6. 06Multi-step confirmation for destructive operations

Use cases

  1. 01Exploring and analyzing Teradata data from Claude Desktop
  2. 02Building RAG and vector retrieval pipelines for AI agents
  3. 03Managing database security, capacity monitoring and backups

MCP support

This is an MCP server that exposes Teradata-related tools, resources and prompts to MCP clients such as Claude Desktop and VS Code.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
"mcpServers": {
"teradata": {
"command": "uvx",
"args": [
"teradata-mcp-server"
],
"env": {
"DATABASE_URI": "<DATABASE_URI>"
}
}
}
}
Run commanduvx teradata-mcp-server
Environment variables to set
DATABASE_URI

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
pypiteradata-mcp-server

Tools

47

Saved tool list · updated 3w ago

ParameterTypeRequiredDescription
fieldsanyNo
table_kindanyNo
max_workersanyNo
object_nameanyNo
database_namestringYes
max_payload_kbanyNo
exclude_objectsanyNo
max_execution_secondsanyNo

Details

From the project README

Teradata MCP Server

docs release PyPI downloads

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

Teradata MCP Server architecture

Quick Start (Choose Your Path)

ClientBest ForSetup Time
Claude DesktopExploratory analysis, platform admin5 min
VS Code + CopilotData engineering, agent development5 min
Open WebUITesting new LLMs locally5 min
Code ExamplesBuild your own clientvaries
FlowiseVisual agent builder10 min

Pre-requisites: Teradata database (or free sandbox) + uv

Claude Desktop Setup (No Installation)

Add this to claude_desktop_config.json (Settings > Developer > Edit Config):

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

What You Can Do

Use CaseCapabilitiesTools
Query & AnalyzeExplore tables, profile data, explain results, visualize patterns—no SQL neededbase, dba, qlty, plot
Semantic LayerGenerate custom semantic layers and tools from YAML or with our Agent SkillLearn more →
AI & RAG PipelinesSemantic search, retrieval-augmented generation, vector storagerag, tdvs, fs
Database AdminManage security, monitor capacity, automate backupsdba, sec, bar

What's New (Latest Release)

  • FastMCP v4 — Sessionless protocol, background tasks for long-running analytics, argument completion
  • Response Caching — 5-minute TTL signals reduce redundant database queries in multi-turn conversations
  • Guard Mode — Multi-step confirmation flows for destructive operations (bar_, sec_)
  • Background Tasks — tdml_* analytic functions return task IDs for polling instead of blocking
  • Argument Completion — Auto-suggest table and column names from schema as users type
  • Hooks Capability — Intercept tool calls for custom monitoring, audit, or rate-limiting
  • Row Limit Protection — Configurable caps (DEFAULT_ROW_LIMIT, MAX_ROW_LIMIT) prevent LLM token overflow
  • Enhanced Security — VX views for fine-grained row-level access control

Extend & Deploy

Add Custom Logic
Use hooks to intercept tool calls for monitoring, audit trails, or validation → Hooks Guide

Define Semantic Layers
Create domain-specific tools, prompts, and cubes in YAML → Customization Guide

Deploy Everywhere
Run as CLI (uv), HTTP server, Docker container, or cloud service → Installation Guide

See It In Action

Learn More

Contributing

We welcome contributions! See our Contributing Guide and Developer Guide to get started.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.