Teradata Mcp Server

Shows detailed column information about a database table via SQLAlchemy, bind parameters if provided (prepared SQL), and return the fully rendered SQL (with literals) in metadata. Arguments: database_name - Database name obj_name - table or view name Returns: ResponseType: formatted response with query results + metadata

Lists databases in the Teradata System. Arguments: scope - Filter scope: 'user' returns only user-created databases (excludes system databases), 'all' returns every database. Defaults to 'user' if not specified. Returns: ResponseType: formatted response with query results + metadata

Execute a SQL query via SQLAlchemy, bind parameters if provided (prepared SQL), and return the fully rendered SQL (with literals) in metadata. Arguments: sql - SQL text, with optional bind-parameter placeholders persist - Set to True to persist the results as a table and reuse it later. Recommended for large result sets. Returns: ResponseType: formatted response with query results + metadata (includes 'volatile_table' field in metadata if persist=True)

Extracts the complete DDL of a Teradata object and saves it to a .sql file. This tool solves the token limit problem by executing the extraction and file save operation directly on the server side, without needing to pass large DDL content through the response. Arguments: database_name - Database name (e.g., 'MKTG_USR') object_name - Object name (e.g., 'SP_LOAD_VARIABLES_ARGUMENTARIO_IAG_FICHA_CLIENTE') object_type - Type of object: 'PROCEDURE', 'TABLE', 'VIEW' (default: 'PROCEDURE') output_dir - Directory where to save the DDL file (default: './ddls_extracted') Returns: ResponseType: formatted response with file path, size, and metadata

Get tables commonly used together by database users, this is helpful to infer relationships between tables via SQLAlchemy, bind parameters if provided (prepared SQL), and return the fully rendered SQL (with literals) in metadata. Arguments: database_name - Database name object_name - table or view name Returns: ResponseType: formatted response with query results + metadata

Multi-step workflow to answer a high-level question using Teradata SQL and the chat_aggregatedCompleteChat tool. The agent first builds a Teradata query, then runs aggregated chat completion, and finally synthesizes a global answer.

The following prompt is used to guide the Teradata DBA in finding opportunities for archiving data. (prompt_type: reporting)

You are a Teradata DBA who is an expert in finding the lineage of tables in a database. (prompt_type: context)

You are a Teradata DBA who is an expert in finding the impact of dropping a table. (prompt_type: reporting)

You are a Teradata DBA who is an expert in assessing the health of a database. (prompt_type: reporting)