Trino MCP Server in Go

What is Trino MCP Server in Go?

A high-performance Model Context Protocol (MCP) server for Trino implemented in Go. It enables AI assistants to seamlessly interact with Trino's distributed SQL query engine through standardized MCP tools.

How to use Trino MCP Server in Go?

Install via Homebrew (brew install mcp-trino), download a pre-built binary, build from source, or use the Docker image. Configure environment variables (TRINO_HOST, TRINO_PORT, TRINO_USER, TRINO_PASSWORD, TRINO_SCHEME) and integrate with Cursor, Claude Desktop, Windsurf, or ChatWise by adding a configuration file.

Key features of Trino MCP Server in Go

• Trino SQL query execution through MCP tools
• Catalog, schema, and table discovery
• STDIO and HTTP transport support
• Server-Sent Events (SSE) support for Cursor and other clients
• Compatible with Cursor, Claude Desktop, Windsurf, ChatWise
• Docker container support

Use cases of Trino MCP Server in Go

• AI assistants running analytical SQL queries against Trino
• Discovering available catalogs, schemas, and tables in a Trino environment
• Retrieving table schemas to understand column names, types, and nullability before querying
• Natural language data exploration, e.g., “What are the top 5 customers by account balance?”

FAQ from Trino MCP Server in Go

How do I install the server?

Install via Homebrew (brew tap tuannvm/mcp && brew install mcp-trino), download a pre-built binary from GitHub Releases, build from source, or use the Docker image ghcr.io/tuannvm/mcp-trino:latest.

What environment variables are needed to configure it?

Provide TRINO_HOST, TRINO_PORT, TRINO_USER, TRINO_PASSWORD; optionally set TRINO_SCHEME (e.g., http). For Docker, pass them via -e flags.

What transport modes are supported?

The server supports both STDIO (default) and HTTP transports with Server-Sent Events (SSE) for clients like Cursor.

Which AI applications are compatible?

Cursor, Claude Desktop, Windsurf, ChatWise, and any MCP-compatible client.

What MCP tools does the server provide?

Five tools: execute_query (run SQL), list_catalogs, list_schemas, list_tables, and get_table_schema.