Happy slice of mcp pizzaMCP.pizza

mcp-oceanbase

MCP.Pizza Chef: oceanbase

This is a family of eight servers published by the OceanBase team. The main one connects to a database and answers questions about it: listing tables, sampling rows, searching stored text by meaning or by keyword, and pulling performance reports for a chosen period. What it wants is a database address, username and password rather than a key. It will also run any command it is handed, including ones that change or drop data, with no read-only mode and nothing asking first.

Coding
Data

Use This MCP server To

Ask what is in a database without writing a query List the tables and peek at a few rows Search stored records by meaning rather than exact words Pull a performance report for a slow half hour Check which machines make up my cluster

README

🌊 Awesome OceanBase MCP

Model Context Protocol (MCP) Server Collection for OceanBase Ecosystem

English | 简体中文

License Python TypeScript

📖 Project Overview

awesome-oceanbase-mcp is a Model Context Protocol (MCP) server repository specifically designed for the OceanBase ecosystem.

🎯 Mission: Enable AI assistants to interact directly with OceanBase databases and ecosystem components through standardized MCP protocols.

✨ Core Values:

  • 🤖 AI-Friendly: Direct database operations within Claude, ChatGPT and other AI assistants
  • 🔒 Secure & Reliable: Provides safe database access and operation mechanisms
  • 🛠️ Complete Ecosystem: Covers the complete OceanBase product and tool chain
  • 🚀 Ready to Use: Simple configuration to get started

🔍 What is MCP?

The Model Context Protocol (MCP) is an open protocol designed to enable seamless integration between AI applications and external data sources and tools. It provides a standardized way for AI models to access the contextual information and capabilities they need.

🚀 Quick Start

Prerequisites

If you don't have an OceanBase database instance yet, please:

mcp-oceanbase FAQ

What do I need to connect?
A database address, port, username and password, supplied as settings before it starts. There is no account to sign up for and no key to buy.
Can I use this to explore a database I did not build?
Yes. It lists tables, samples rows and answers questions about them, as long as the login you give it has permission to read them.
Can it damage my data?
Yes. It runs whatever command it is given and saves the result, including deleting rows or dropping whole tables. There is no read-only mode and no confirmation step.
How do I protect myself then?
The only real safeguard is the database login you hand it. Create a user that can only read, and point the server at that instead of an administrator account.
Is it protected when run over a network?
There is an optional list of permitted access tokens, and that check is genuinely applied. Without it, anyone who can reach the address can use it.
Does the built-in documentation search work in English?
Poorly. That particular tool states outright that its search word must be in Chinese.
How hard is the setup?
Developer-level. You install a Python package, supply the connection settings yourself and need a running OceanBase database to point it at.
Is it maintained?
Yes. It comes from OceanBase themselves, is Apache licensed and was last updated in June 2026.