Integrate OceanBase MCP Server with Claude Code

The Model Context Protocol (MCP) was introduced and open-sourced by Anthropic in November 2024. It lets large language models interact with external tools and data sources. With MCP, you don't have to copy model output and run it manually—the model can instruct tools to perform actions directly.

The OceanBase MCP Server uses MCP to give LLMs access to OceanBase Database so they can run SQL. With an MCP-capable client you can quickly prototype applications. The server is open source on GitHub.

Claude Code is an AI coding tool from Anthropic. It runs in the terminal as an intelligent coding assistant and helps developers turn ideas into production-quality code quickly.

This topic uses Claude Code to show how to build a backend application quickly with the OceanBase MCP Server.

Prerequisites

• You have deployed OceanBase Database and created a MySQL-compatible tenant. For details, see Create a tenant.

• You have Python 3.11 or later and pip installed. If your system Python is older, use Miniconda to create a Python 3.11+ environment.

• You have Git installed for your OS:

  • Windows: https://git-scm.com/downloads/win
  • macOS: https://git-scm.com/download/mac
  • Linux: https://git-scm.com/downloads/linux

• You have the Python package manager uv installed:

  • macOS/Linux (standalone script):

    curl -LsSf https://astral.sh/uv/install.sh | sh
    

  • Windows (PowerShell):

    irm https://astral.sh/uv/install.ps1 | iex
    

  • Or install with pip on any platform:

    pip install uv
    

  • Verify the installation:

    uv --version
    

• Claude Code is installed:

  1. Open VS Code (install it from the official site if needed).

  2. Click the Extensions icon in the sidebar.

  3. Search for Claude Code and install it.

  4. Configure Claude Code environment variables. For example, add the following to your shell config (e.g. ~/.zshrc):

     export ANTHROPIC_BASE_URL=*****
     export ANTHROPIC_API_KEY=*******
     export ANTHROPIC_MODEL=*******
     

     Then run source ~/.zshrc (or the equivalent for your shell).

  5. Test the connection.

  6. Select your Anthropic model.

Step 1: Get database connection details

Obtain the database connection string from your OceanBase deployment team or administrator. For example:

obclient -h$host -P$port -u$user_name -p$password -D$database_name

Parameters:

• $host: The IP for connecting to OceanBase. Use an ODP address when connecting via OceanBase Database Proxy (ODP), or an OBServer IP for direct connection.

• $port: The connection port. ODP default is 2883; direct connection default is 2881. Both can be customized at deployment.

• $database_name: The database to use.

  Notice

  The user connecting to the tenant must have CREATE, INSERT, DROP, and SELECT privileges on that database. For more on privileges, see Privilege types in MySQL-compatible mode.

• $user_name: The tenant account. ODP: username@tenant#cluster or cluster:tenant:username. Direct: username@tenant.

• $password: The account password.

For more on connection strings, see Connect to an OceanBase tenant by using OBClient.

Step 2: Configure the OceanBase MCP Server

Clone the OceanBase MCP Server repository

Download the source:

git clone https://github.com/oceanbase/awesome-oceanbase-mcp.git

Change into the project directory:

cd awesome-oceanbase-mcp

Install dependencies

From the oceanbase_mcp_server directory, create a virtual environment and install dependencies:

uv venv
source .venv/bin/activate
uv pip install .

Configure the OceanBase MCP Server

1. Open the terminal in VS Code and run the claude mcp add-json command. Replace /path/to/your/oceanbase_mcp_server with the absolute path to the oceanbase_mcp_server folder, and set OB_HOST, OB_PORT, OB_USER, OB_PASSWORD, and OB_DATABASE to your database values.

   claude mcp add-json oceanbase '{
     "command": "uv",
     "args": [
       "--directory",
       "/path/to/your/oceanbase_mcp_server/src/oceanbase_mcp_server",
       "run",
       "oceanbase_mcp_server"
     ],
     "env": {
       "OB_HOST": "***",
       "OB_PORT": "***",
       "OB_USER": "***",
       "OB_PASSWORD": "***",
       "OB_DATABASE": "***"
     }
   }'
   

2. Verify the connection. In the chat, ask: How many tables are in the test database? Claude Code will show the SQL it plans to run and then the query result.

   Claude Code will show the number of tables in the test database, confirming that the connection to OceanBase is working.

Step 3: Build a RESTful API with FastAPI

FastAPI is a Python web framework well-suited for building RESTful APIs.

1. Create the table. Use the prompt: Create a customer table with primary key ID and columns name, age, telephone, and location.

2. Insert test data. Use the prompt: Insert 10 rows of test data.

3. Create the FastAPI project. Use the prompt: Create a FastAPI project that exposes a RESTful API for the customer table. Claude Code will generate the files. Adjust the code if anything needs to be changed.

4. Install dependencies.

   cd customer_api
   pip install -r requirements.txt
   

5. Start the FastAPI app.

   python3 main.py
   

6. Query the API. From a terminal or any HTTP client:

   curl http://127.0.0.1:8000/customers
   

   The response will contain the customer records. The generated code implements full CRUD (create, read, update, delete) for the customer table.

   Example generated code:

   from sqlalchemy.orm import Session
   from . import models, schemas
   from typing import List, Optional
   
   def get_customer(db: Session, customer_id: int):
       return db.query(models.Customer).filter(models.Customer.ID == customer_id).first()
   
   def get_customers(db: Session, skip: int = 0, limit: int = 100):
       return db.query(models.Customer).offset(skip).limit(limit).all()
   
   def create_customer(db: Session, customer: schemas.CustomerCreate):
       db_customer = models.Customer(**customer.dict())
       db.add(db_customer)
       db.commit()
       db.refresh(db_customer)
       return db_customer
   
   def update_customer(db: Session, customer_id: int, customer: schemas.CustomerUpdate):
       db_customer = db.query(models.Customer).filter(models.Customer.ID == customer_id).first()
       if db_customer:
           update_data = customer.dict(exclude_unset=True)
           for key, value in update_data.items():
               setattr(db_customer, key, value)
           db.commit()
           db.refresh(db_customer)
       return db_customer
   
   def delete_customer(db: Session, customer_id: int):
       db_customer = db.query(models.Customer).filter(models.Customer.ID == customer_id).first()
       if db_customer:
           db.delete(db_customer)
           db.commit()
           return True
       return False
   
   def search_customers(db: Session, name: Optional[str] = None, location: Optional[str] = None):
       query = db.query(models.Customer)
       if name:
           query = query.filter(models.Customer.name.contains(name))
       if location:
           query = query.filter(models.Customer.location.contains(location))
       return query.all()