Skip to main content
Glama
Teradata

Teradata MCP Server

Official
by Teradata

base_readQuery

Read-onlyIdempotent

Execute SQL queries on Teradata databases with bind parameter support, optional result persistence as tables, and configurable row limits up to 50,000.

Instructions

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. row_limit - Maximum rows to return (default 1000, ceiling 50000). Pass a higher value when you need more rows.

When the response metadata contains 'truncated: true', more rows exist beyond the limit. To get more data:

  • Pass a higher row_limit (up to 50000) to retrieve more rows in the response.

  • Use persist=true to write all rows to a volatile table and query it directly — this bypasses the row limit entirely and is the recommended approach for large result sets.

Returns: ResponseType: formatted response with query results + metadata (includes 'volatile_table' field in metadata if persist=True) (includes 'truncated' and 'row_limit' in metadata when results are capped)

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
sqlNo
persistNo
row_limitNo
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Description discloses behavior of persist=True writing to a volatile table, which contradicts the readOnlyHint=true annotation. This is a significant inconsistency that could mislead an agent.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Well-structured with sections, but the truncation handling is somewhat verbose. Could be more concise while retaining essential information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no output schema, description thoroughly explains return metadata (volatile_table, truncated, row_limit) and how to use them. Covers edge cases like truncation and persistence.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Despite 0% schema coverage, the description explains all three parameters: sql (text with placeholders), persist (boolean for persisting), row_limit (default 1000, ceiling 50000, and how to use for larger results). Provides usage nuances.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it executes SQL queries via SQLAlchemy with bind parameters, and distinguishes from sibling tools that focus on metadata, graphs, or quality checks. It includes specific actions: execute, bind, return rendered SQL.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides clear guidance on when to use persist=True and how to handle truncated results (increase row_limit or persist). Lacks explicit comparison to alternative tools or when not to use.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/Teradata/teradata-mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server