Name: Trino MCP Server in Go
Author: tuannvm

LABSCO SUMMARY

Discovery first, then the query.

The four listing tools exist so an assistant finds the right catalog, schema and table before it writes any SQL, and the plan tool lets it read what a query will do before the cluster spends time on it. On a large deployment the allowlist variables are what make that workable — restrict it to the handful of schemas that matter and it stops wandering through catalogs nobody asked about.

What it is

A Go MCP server for Trino, the distributed SQL query engine formerly called PrestoSQL. The same binary doubles as an interactive CLI in the shape of psql. It runs over STDIO or Streamable HTTP, with SSE endpoints kept for backward compatibility, and optional OAuth 2.1 through the oauth-mcp-proxy library with HMAC, Okta, Google and Azure AD as providers.

What you get

SQL run against Trino with the columns and rows returned as structured data — execute_query
Discovery down the hierarchy so the model finds the right table before writing SQL — list_catalogs, list_schemas, list_tables, get_table_schema, the last returning column names, types and nullability
A query's distributed execution plan with stages and estimated rows and cost, read without running the query — explain_query
An interactive CLI on the same binary: mcp-trino --interactive for a REPL, mcp-trino query to run one statement, plus catalogs, schemas, tables, describe and explain subcommands, with output as table (the default), json or csv
REPL meta-commands for the same moves — \catalogs, \schemas, \tables, \describe, \format, \history
Named connection profiles in ~/.config/trino/config.yaml or config.json, switched with mcp-trino config profile use prod or per-command with --profile dev; when both files exist the JSON one wins
Allowlists that shrink what the assistant can even see, at catalog, schema and table level, case-insensitive and independent of each other — TRINO_ALLOWED_CATALOGS, TRINO_ALLOWED_SCHEMAS, TRINO_ALLOWED_TABLES
Query attribution: with OAuth enabled, queries are automatically tagged with the OAuth user through the X-Trino-Client-Tags and X-Trino-Client-Info headers, and opt-in impersonation sends X-Trino-User so Trino applies that user's own permissions — TRINO_ENABLE_IMPERSONATION, TRINO_IMPERSONATION_FIELD
Exit codes worth scripting against: 0 success, 1 runtime error such as a failed connection or query, 2 usage error
Distribution as a Homebrew formula, an install script and a Docker image on GitHub Container Registry, with SBOM and SLSA provenance published per release

Requirements

A reachable Trino cluster and its connection details in the environment: TRINO_HOST, TRINO_PORT, TRINO_USER, TRINO_PASSWORD, TRINO_CATALOG, TRINO_SCHEMA and TRINO_SSL; a local development run needs only TRINO_HOST and TRINO_USER. Install with brew install tuannvm/mcp/mcp-trino or the install script from the repository. Secrets are read purely from the process environment, and the README's recommended pattern is injecting them at launch from a secrets CLI such as 1Password or Vault rather than writing them to disk. OAuth is optional: OAUTH_ENABLED, OAUTH_MODE (native keeps all secrets on the client side, proxy centralises them on the server), OAUTH_PROVIDER, OIDC_ISSUER and OIDC_AUDIENCE, with OIDC_CLIENT_ID, OIDC_CLIENT_SECRET and OAUTH_REDIRECT_URI added in proxy mode; JWT_SECRET is required for multi-pod deployments. MIT licensed.

Setup effort

One command plus credentials — brew install tuannvm/mcp/mcp-trino, then supply credentials

See installation options

USE CASES

Answering an analytics question without writing the SQL yourself

Let the assistant walk catalogs, schemas and tables to find the data, then run the query and read back columns and rows.

list_catalogslist_schemaslist_tablesexecute_query

Checking what a query will do before it runs

Read the execution plan with its stages and estimated rows and cost, then decide whether to run it against production data.

explain_query

Understanding an unfamiliar table

List the tables in the schema, then read the column names, types and nullability before writing anything against it.

list_tablesget_table_schema

Keeping the assistant inside the schemas that matter

Set the allowlist variables to the catalogs, schemas or tables you want visible — anything else disappears from discovery.

Telling from Trino's side who ran what

Enable OAuth so queries carry the user in the client tag headers, and turn on impersonation when you want Trino to enforce that user's own permissions.

6 tools

Listed in project docs. Your client may show a different list.

execute_query

list_catalogs

list_schemas

list_tables

get_table_schema

explain_query

INSTALLATION

Connect your client

Server setup

Install the binary: brew install tuannvm/mcp/mcp-trino, or curl -fsSL https://raw.githubusercontent.com/tuannvm/mcp-trino/main/install.sh | bash, or download a release binary and chmod +x it, or build from source (git clone https://github.com/tuannvm/mcp-trino.git; cd mcp-trino; make build)

Add the mcpServers block to your client config (~/.cursor/mcp.json, claude_desktop_config.json, Windsurf mcp_config.json) with your TRINO_* env values — or for Claude Code run: claude mcp add mcp-trino mcp-trino and export the TRINO_* variables

For HTTP transport instead of stdio, start the server separately (MCP_TRANSPORT=http ... mcp-trino) and point the client at http://localhost:8080/mcp

MCP Clients

Cursor

CURSOR · JSON

{
  "mcpServers": {
    "mcp-trino": {
      "command": "mcp-trino",
      "args": [],
      "env": {
        "TRINO_HOST": "<YOUR_TRINO_HOST>",
        "TRINO_PORT": "<YOUR_TRINO_PORT>",
        "TRINO_USER": "<YOUR_TRINO_USER>",
        "TRINO_PASSWORD": "<YOUR_TRINO_PASSWORD>"
      }
    }
  }
}

Any MCP client — Docker

ANY MCP CLIENT — DOCKER · JSON

{
  "mcpServers": {
    "mcp-trino": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "-e",
        "TRINO_HOST=<YOUR_TRINO_HOST>",
        "-e",
        "TRINO_PORT=<YOUR_TRINO_PORT>",
        "-e",
        "TRINO_USER=<YOUR_TRINO_USER>",
        "-e",
        "TRINO_PASSWORD=<YOUR_TRINO_PASSWORD>",
        "-e",
        "TRINO_SCHEME=http",
        "ghcr.io/tuannvm/mcp-trino:latest"
      ],
      "env": {}
    }
  }
}

Any MCP client — HTTP

ANY MCP CLIENT — HTTP · JSON

{
  "mcpServers": {
    "mcp-trino-http": {
      "url": "http://localhost:8080/mcp"
    }
  }
}

Any MCP client — JWT

ANY MCP CLIENT — JWT · JSON

{
  "mcpServers": {
    "mcp-trino-remote": {
      "url": "<YOUR_SERVER_URL>/mcp",
      "headers": {
        "Authorization": "Bearer <YOUR_JWT_TOKEN>"
      }
    }
  }
}

Any MCP client — SSE

ANY MCP CLIENT — SSE · JSON

{
  "mcpServers": {
    "mcp-trino-sse": {
      "url": "http://localhost:8080/sse"
    }
  }
}

Claude Desktop

CLAUDE DESKTOP · JSON

{
  "mcpServers": {
    "mcp-trino": {
      "command": "mcp-trino",
      "args": [],
      "env": {
        "TRINO_HOST": "<YOUR_TRINO_HOST>",
        "TRINO_PORT": "<YOUR_TRINO_PORT>",
        "TRINO_USER": "<YOUR_TRINO_USER>",
        "TRINO_PASSWORD": "<YOUR_TRINO_PASSWORD>"
      }
    }
  }
}

Add to claude_desktop_config.json (macOS: ~/Library/Application Support/Claude/, Windows: %APPDATA%\Claude\, Linux: ~/.config/Claude/), then restart Claude Desktop.

Windsurf

WINDSURF · JSON

{
  "mcpServers": {
    "mcp-trino": {
      "command": "mcp-trino",
      "args": [],
      "env": {
        "TRINO_HOST": "<YOUR_TRINO_HOST>",
        "TRINO_PORT": "<YOUR_TRINO_PORT>",
        "TRINO_USER": "<YOUR_TRINO_USER>",
        "TRINO_PASSWORD": "<YOUR_TRINO_PASSWORD>"
      }
    }
  }
}

Add to Windsurf's mcp_config.json, then restart Windsurf.

Chatwise

CHATWISE · JSON

{
  "mcpServers": {
    "mcp-trino": {
      "command": "mcp-trino",
      "args": [],
      "env": {
        "TRINO_HOST": "<YOUR_TRINO_HOST>",
        "TRINO_PORT": "<YOUR_TRINO_PORT>",
        "TRINO_USER": "<YOUR_TRINO_USER>",
        "TRINO_PASSWORD": "<YOUR_TRINO_PASSWORD>"
      }
    }
  }
}

Copy this JSON, then in ChatWise Settings > Tools click "+" and choose "Import JSON from Clipboard".

Trino MCP Server in Go

Discovery first, then the query.

What it is

What you get

Requirements

Setup effort

Answering an analytics question without writing the SQL yourself

Checking what a query will do before it runs

Understanding an unfamiliar table

Keeping the assistant inside the schemas that matter

Telling from Trino's side who ran what

6 tools

What to know first

Tools you get

Requires

Connect your client

Server setup

MCP Clients

Cursor

Any MCP client — Docker

Any MCP client — HTTP

Any MCP client — JWT

Any MCP client — SSE

Claude Desktop

Windsurf

Chatwise

Trino MCP Server in Go

Discovery first, then the query.

What it is

What you get

Requirements

Setup effort

Answering an analytics question without writing the SQL yourself

Checking what a query will do before it runs

Understanding an unfamiliar table

Keeping the assistant inside the schemas that matter

Telling from Trino's side who ran what

6 tools

What to know first

Tools you get

Requires

Connect your client

Server setup

MCP Clients

Cursor

Any MCP client — Docker

Any MCP client — HTTP

Any MCP client — JWT

Any MCP client — SSE

Claude Desktop

Windsurf

Chatwise

Same category

MCP PostgreSQL Server

ChatQL MCP Server

PostgreSQL Database Query Server

Go MCP Postgres