Teradata Vantage
Connect AI agents and workflows to Teradata Vantage: run SQL, read databases and tables, insert and update rows, call procedures and macros, act on new rows.
Book a demoTeradata Vantage for AI agents and workflows.
engini lets your AI agents and workflows work in Teradata Vantage, on premises or on VantageCloud: run SQL with parameters, read databases, tables and views, insert, update and delete rows, call stored procedures and macros, load rows in bulk, and start a workflow when new rows arrive. Decades of history in the warehouse reach the agents and systems that act on it. Connect from Claude, ChatGPT or Cursor over MCP, from your code, or build in Workflow Studio.
Cursor, your code
audit log
in engini
What your agent can do in Teradata Vantage. Every tool is one you allow or leave out.
The Teradata Vantage tools in engini, grouped by what they change. Read tools are safe to hand out widely. Write and delete tools go only to the agents that need them.
Read
Run a SQL query with parameters and get the rows back.
Read what is in the warehouse and how it is shaped.
Write
Write rows in a transaction.
Load many rows at once, through Teradata's bulk path.
Run a stored procedure or macro with its parameters.
Run any statement you allow, such as MERGE.
Delete
Remove rows that match a condition.
Triggers
Rows added to a table, by an increasing column such as a timestamp or ID.
A query you write returns rows, such as a metric crossing a threshold.
A trigger starts a workflow, and a workflow can include an AI agent step. In Code, a trigger delivers the event to your own endpoint.
Connect your AI agent to Teradata Vantage. Four ways in, one set of permissions.
Claude, ChatGPT, Cursor
Create an MCP server in engini with your Teradata Vantage connection and only the tools you choose. Add its address to your client and sign in through engini. There is no key to copy.
MCP client setup →Python and TypeScript
Hand your agent a toolset of Teradata Vantage tools. The SDK gives OpenAI and Anthropic models the tools in the format they expect and runs the ones they pick.
SDK guide →For coding agents
The engini CLI connects Teradata Vantage and runs its tools from a terminal, with machine-readable output, so an AI coding agent can drive it without getting stuck.
CLI guide →Any language
Every Teradata Vantage tool is an endpoint. Call it with exact inputs from a scheduled job or a sync, with no model in the loop.
API reference →.cursor/mcp.json. Claude Code: claude mcp add.// .cursor/mcp.json: Cursor, connected to Teradata Vantage through engini
{
"mcpServers": {
"engini-teradata": {
"url": "<your engini MCP server address>"
}
}
}
Create the MCP server in engini with your Teradata Vantage connection and the tools this agent may use, then paste its address. The client signs in through engini on first use. Claude, VS Code and other clients take the same address: see the MCP client setup guide.
Each request runs through the Teradata Vantage tools in the agent's toolset or MCP server. If a tool is not allowed, the agent cannot call it.
What teams build on Teradata Vantage. Agents and workflows, across systems.
Systems of record into Teradata
Orders, invoices and cases from NetSuite, Salesforce and ServiceNow load into Teradata on a schedule, with no pipeline code.
Warehouse scores in the CRM
Propensity and churn scores computed in Teradata are written back to Salesforce accounts.
Metrics that alert
A scheduled query watches a metric and posts to Teams or Slack when it crosses a line.
Questions in plain words
An agent in Claude turns a question into SQL and answers with the numbers. Its toolset holds read tools only.
Every integration runs both ways, so any of these flows can also run in reverse. These are examples, not the limit: any flow between Teradata Vantage and another system engini connects is available.
You decide what each agent may do in Teradata Vantage. engini enforces it on every call.
Only the tools you allow
A toolset lists the Teradata Vantage tools an agent may call and the connection each one uses. Give one agent read tools only and another the write it needs. engini refuses any call outside the toolset.
Scoped when you set them up
An MCP server exposes only the connections and tools chosen when it is created, and engini shows who uses each server.
Whose permissions apply
Connect a person's own Teradata Vantage account and engini acts as that person, with their Teradata Vantage permissions. Use a shared integration account and it acts as that account. Every run is recorded under the user who started it.
Kept out of prompts
Your agent never needs your credentials: engini stores them and adds them when it runs each call, so keys stay out of prompts and tool inputs.
Every call on record
Every call lands in History and the audit log, which you can export or stream to your SIEM.
Test before production
Workspaces keep teams apart, and development, staging and production environments keep a test agent away from live data.
Teradata behind your firewall.
If Teradata runs in your own data center, install the engini On-Prem Agent on a server inside your network. It opens every connection itself: out to engini over HTTPS on port 443, and to Teradata while it runs a task. You open no inbound ports or firewall rules. Calls through it run on the same engine as MCP, the API and workflows, and each one is recorded in History.
On-Prem Agent guide →Connect Teradata Vantage in three steps. Then decide what each agent may do.
Sign in to Teradata Vantage
Create a Teradata user with access only to the databases the workflows need, then add a Teradata connection with the host and that user, through the On-Prem Agent if the system runs inside your network.
Choose the tools
Add the connection to an MCP server or a toolset with only the tools each agent needs.
Build or ask
Use the connection as a step in a workflow, or ask your agent to work in Teradata Vantage from Claude, ChatGPT, Cursor or your own code.
Teradata Vantage and engini. Straight answers.
Can an AI agent write to Teradata Vantage, or only read?
Both. engini has tools to insert, update and delete rows, load rows in bulk, call stored procedures and macros, and run statements you allow. Whether a given agent may use them is up to you: give it a toolset or an MCP server with read tools only, and it cannot call the rest.
How do I keep a read-only agent read-only?
Give its toolset Run Query and the other read tools only, and use a Teradata user with SELECT rights only. engini refuses tools outside the toolset, and Teradata refuses writes the user cannot make.
Does it work with VantageCloud and on premises?
Yes. Connect VantageCloud directly, or an on-premises system through the On-Prem Agent.
Does the agent act as me in Teradata Vantage?
It acts as the Teradata user behind the connection, with that user's grants. Every run is recorded under the person who started it.
Can a change in Teradata Vantage start work?
Yes. Scheduled triggers check a table for new rows, or run a query you write and start work when it returns rows. A workflow can include an AI agent step.