What is MCP?
MCP (Model-Control-Protocol) is a protocol for bridging AI models, data, and tools. This server implements MCP to expose Trino tables and query capabilities.
Trino MCP Server
@MCP-Mirror
Basic information
About Trino MCP Server
Mirror of
Trino MCP Server config
No standard config provided
This server doesn't expose a parseable MCP config block in its README. See the repository for install instructions.
RepositoryTrino MCP Server tools
Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Overview
What is Trino MCP Server?
This server provides an MCP (Model-Control-Protocol) interface for listing and querying tables via Trino using Python. It connects to a Trino host using the trino.dbapi Python client and exposes tables as MCP resources, allows reading table contents, and provides a tool to execute arbitrary SQL queries. It is intended for AI models and MCP clients that need to interact with Trino data sources.
How to use Trino MCP Server?
Configure the required Trino connection details via environment variables (TRINO_HOST, TRINO_PORT, TRINO_USER, TRINO_CATALOG, TRINO_SCHEMA, optionally TRINO_PASSWORD). Then run the server by adding it to your MCP client configuration using uv with the command uv --directory <path_to_server> run mcp_server_trino and the necessary environment variables.
Key features of Trino MCP Server
- List Trino tables as MCP resources.
- Read table contents through MCP.
- Execute arbitrary SQL queries via a tool.
- Connects using Trino’s Python client (
trino.dbapi). - Fully configurable via environment variables.
Use cases of Trino MCP Server
- AI assistants exploring and querying Trino data catalogs.
- Listing available tables in a Trino schema from an MCP client.
- Running ad‑hoc SQL queries against Trino through AI tools.
- Integrating big data analytics with conversational AI workflows.
Frequently asked questions
What environment variables are required?
You must set `TRINO_HOST`, `TRINO_PORT`, `TRINO_USER`, `TRINO_CATALOG`, and `TRINO_SCHEMA`. `TRINO_PASSWORD` is optional and depends on your Trino authentication setup.
What dependencies does the server need?
Python 3.9+ along with the `trino` and `mcp` Python packages.
Can I run SQL queries other than SELECT?
Yes, the server includes a tool for executing arbitrary SQL queries against Trino, subject to Trino’s permissions.
How does the server connect to Trino?
It uses the `trino.dbapi` Python client and requires a host, port, user, catalog, and schema. Password authentication is optional.
More Other MCP servers
P
PickFu MCP
PickFu MCP is a Model Context Protocol (MCP) server that connects AI assistants, developers, marketers, product managers, and AI agents to PickFu's consumer research platform. It enables users to create surveys, conduct
Hindsight
vectorize-ioHindsight: Agent Memory That Learns
50.4K
Senso MCP for Joomla
sensomediaSenso MCP turns a Joomla 5 or 6 site into a remote MCP server. It runs inside Joomla itself (no extra server, no Node.js bridge) and is secured with OAuth 2.1 and Joomla's own ACL. The free pack lets an AI assistant crea
YOUB
Connect your AI assistant to your own YOUB endurance training account. Read recorded activities with full analysis, planned sessions, race goals, wellness (HRV, sleep, resting HR) and your athletic profile. Create or mov
Maestro
mobile-dev-incPainless E2E Automation for Mobile and Web
14.8K
Comments