Trino MCP Server
by Dataring-engineering
This repository provides an MCP server that allows you to list and query tables via Trino using Python. It bridges AI models, data, and tools by providing access to Trino tables and enabling SQL query execution.
Last updated: N/A
What is Trino MCP Server?
This is an MCP (Model-Control-Protocol) server that exposes Trino tables as MCP resources. It allows listing tables, reading table contents, and executing arbitrary SQL queries against a Trino instance.
How to use Trino MCP Server?
- Configure the server by setting the required environment variables (TRINO_HOST, TRINO_PORT, TRINO_USER, TRINO_PASSWORD, TRINO_CATALOG, TRINO_SCHEMA). 2. Install the necessary Python packages (trino, mcp). 3. Run the server using the provided configuration example.
Key features of Trino MCP Server
Lists Trino tables as MCP resources
Reads table contents through MCP
Executes arbitrary SQL queries against Trino
Uses Trino's Python client (trino.dbapi) for connectivity
Use cases of Trino MCP Server
Integrating Trino data with AI models
Providing a standardized interface for accessing Trino data
Building data pipelines that leverage Trino's query capabilities
Enabling data discovery and exploration through MCP
FAQ from Trino MCP Server
What is MCP?
What is MCP?
MCP is a protocol for bridging AI models, data, and tools.
What is Trino?
What is Trino?
Trino is a fast, distributed SQL query engine for big data analytics.
What Python version is required?
What Python version is required?
Python 3.9+ (or a version compatible with mcp, trino, and asyncio)
What environment variables are required?
What environment variables are required?
TRINO_HOST, TRINO_PORT, TRINO_USER, TRINO_CATALOG, and TRINO_SCHEMA are required. TRINO_PASSWORD is optional.
How do I run the server?
How do I run the server?
Install the required dependencies and use the provided configuration example to run the server.