MCP Trino Python MCP Server

The MCP Trino Server is a [Model Context Protocol (MCP)](https://modelcontextprotocol.io/introduction) server that provides seamless integration with

Local serverstdioPython

What is the MCP Trino Python MCP server?

If you want an AI assistant working directly with MCP Trino Python, the mcp trino python mcp server is the bridge. The MCP Trino Server is a Model Context Protocol (MCP) server that provides seamless integration with Trino and Iceberg, enabling advanced data exploration, querying, and table maintenance capabilities through a standard interface.

What MCP Trino Python does

The MCP Trino Server is a Model Context Protocol (MCP) server that provides seamless integration with Trino and Iceberg, enabling advanced data exploration, querying, and table maintenance capabilities through a standard interface.

Tools it exposes

Once connected, the assistant can call these 12 tools directly:

  • show_catalogs — List all available catalogs
  • show_schemas — List all schemas in a catalog
  • Parameters — - catalog: Catalog name (string, required)
  • show_tables — List all tables in a schema
  • schema — Schema name (string, required)
  • describe_table — Show detailed table structure and column information
  • catalog — Catalog name (string, optional)
  • execute_query — Execute a SQL query and return formatted results
  • show_catalog_tree — Show a hierarchical tree view of catalogs, schemas, and tables
  • show_create_table — Show the CREATE TABLE statement for a table
  • show_create_view — Show the CREATE VIEW statement for a view
  • show_stats — Show statistics for a table

Installing the mcp trino python mcp server

The server is distributed via npm as @smithery/cli, so most clients can run it without a manual build step. Add it to your MCP client's configuration and restart the client to pick it up — the copy-paste configs for Claude Desktop, Claude Code and Cursor are on this page.

Configuration

The server reads 3 environment variables: TRINO_HOST, TRINO_PORT, TRINO_USER. Keep credentials in your client's env block or a secrets manager rather than committing them.

Requirements

  1. A running Trino server (or Docker Compose for local development) 2. Python 3.12 or higher 3. Docker (optional, for containerized deployment)

Where it fits

Database servers turn schema archaeology and ad-hoc reporting into conversation, which is why they tend to be the second or third server people install. MCP Trino Python sits in that group, and the shape of its toolset — show_catalogs, show_schemas, Parameters among others — tells you what it is really for. Worth comparing against the other databases servers in this directory before you commit to one, since several overlap in scope but differ sharply in setup cost and permissions.

Practical notes

  • This server runs locally, so it operates with whatever access your machine and its credentials already have. Scope that deliberately rather than by default.
  • With 12 tools exposed, expect a noticeable bump in prompt size — disable it in projects that never use MCP Trino Python.
  • Maintained by alaturqua, written in Python.
  • MCP clients ask for confirmation before each tool call by default. Keep that on while you learn what the mcp trino python mcp server actually does with your data.
  • Every entry in this directory is reviewed by hand before it goes live, and details are checked against the project's own documentation.

Available tools

ToolWhat it does
show_catalogsList all available catalogs
show_schemasList all schemas in a catalog
Parameters- catalog: Catalog name (string, required)
show_tablesList all tables in a schema
schemaSchema name (string, required)
describe_tableShow detailed table structure and column information
catalogCatalog name (string, optional)
execute_queryExecute a SQL query and return formatted results
show_catalog_treeShow a hierarchical tree view of catalogs, schemas, and tables
show_create_tableShow the CREATE TABLE statement for a table
show_create_viewShow the CREATE VIEW statement for a view
show_statsShow statistics for a table

How to install the MCP Trino Python MCP server

{
  "mcpServers": {
    "trino-python": {
      "command": "npx",
      "args": ["-y", "@smithery/cli"],
      "env": {
        "TRINO_HOST": "your-value",
        "TRINO_PORT": "your-value",
        "TRINO_USER": "your-value"
      }
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Configuration

  1. A running Trino server (or Docker Compose for local development) 2. Python 3.12 or higher 3. Docker (optional, for containerized deployment)
VariableDescriptionRequired
TRINO_HOSTEndpoint or connection string the server talks to.Optional
TRINO_PORTConfiguration value read at startup.Optional
TRINO_USERConfiguration value read at startup.Optional

Example prompts to try

  • Use MCP Trino Python to show catalogs.
  • Use MCP Trino Python to show schemas.
  • Use MCP Trino Python to Parameters.

Frequently asked questions

It connects MCP Trino Python to MCP-compatible AI assistants such as Claude and Cursor, exposing 12 tools (show_catalogs, show_schemas, Parameters, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with MCP Trino Python directly.