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.
@MCP-Mirror
基本情報
Mirror of
ツール一覧はまだありません
この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。
ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。
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.
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.
trino.dbapi).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.
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.
Python 3.9+ along with the `trino` and `mcp` Python packages.
Yes, the server includes a tool for executing arbitrary SQL queries against Trino, subject to Trino’s permissions.
It uses the `trino.dbapi` Python client and requires a host, port, user, catalog, and schema. Password authentication is optional.
🚀 The fast, Pythonic way to build MCP servers and clients.
This open-source curriculum introduces the fundamentals of Model Context Protocol (MCP) through real-world, cross-language examples in .NET, Java, TypeScript, JavaScript, Rust and Python. Designed for developers, it focuses on practical techniques for building modular, scalable,

Model Context Protocol Servers
YC (S26) | Open Computer History | Continuously record your company computer work, map your workflows, help you find work worth automating, and power your agents' context

Handl speaks the Model Context Protocol. Your whole billing operation — projects, invoices, clients, reports, approvals — as tools any AI assistant can call, inside your autonomy rules.
コメント