Sample For Bedrock Integration With Database MCP Server

🚀 Amazon Bedrock Converse API Integration with Database MCP Server Example

This example demonstrates how to integrate the conversational AI capabilities of AWS Bedrock with a relational database through the Model Context Protocol (MCP). Specifically, it's an example of using Bedrock to perform natural - language queries on a database.

🚀 Quick Start

Architecture Diagram

Component Description

Installation Steps

1. Clone the code repository

Use the following command to clone the example code:

git clone https://github.com/your-username/chat-with-database.git

2. Install dependencies

Run the following command to install the required Python packages:

pip install -r requirements.txt

3. Configure the database connection

Modify the config/database_config.py file and fill in your database information:

DATABASE_TYPE = 'sqlite'  # Or 'postgres'
SQLITE_DB_NAME = 'mymcpdb.db'  # Default SQLite database name
POSTGRES_CONFIG = {
    'host': 'your-rds-endpoint',
    'database': 'your-database-name',
    'user': 'your-db-user',
    'password': 'your-db-password',
    'ssl_cert_path': '/path/to/global-bundle.pem'
}

4. Start the application

Run the following command to start the program:

cd src
python3 chat.py --db-type [sqlite/postgres]

💻 Usage Examples

Basic Usage

• List all users:

  Query all records in the users table.
  

• Sort products by price:

  Sort the products in the products table by price in descending order.
  

🔧 Technical Details

Cost Estimation

1. RDS PostgreSQL database: It is billed according to the instance type and usage duration. For specific fees, refer to Amazon RDS Pricing.
2. Bedrock Claude model invocation API: The cost is determined by the number of invocations and the selected model version. For detailed information, see Bedrock Pricing.
3. Guardrail service: It provides additional security protection features. For cost reference, see Guardrail Pricing.

Supplementary Notes

Test Data Table Structure

Users Table

CREATE TABLE users (
    id SERIAL PRIMARY KEY,
    name VARCHAR(255) NOT NULL,
    email VARCHAR(255) UNIQUE NOT NULL,
    created_at TIMESTAMP WITH TIME ZONE DEFAULT CURRENT_TIMESTAMP
);

Example Data Insertion

INSERT INTO users (name, email) VALUES
    ('John Doe', 'john.doe@example.com'),
    ('Jane Smith', 'jane.smith@example.com'),
    ('Bob Wilson', 'bob.wilson@example.com'),
    ('Alice Johnson', 'alice.j@example.com'),
    ('Tom Brown', 'tom.brown@example.com');

Products Table

CREATE TABLE products (
    product_id SERIAL PRIMARY KEY,
    name VARCHAR(255) NOT NULL,
    price DECIMAL(10,2) NOT NULL
);

INSERT INTO products (name, price) VALUES
    ('Amazon Echo Dot (5th Gen)', 49.99),
    ('Kindle Paperwhite 8GB', 139.99),
    ('Fire TV Stick 4K', 49.99),
    ('Ring Video Doorbell', 99.99),
    ('Amazon Smart Plug', 24.99);

These tables and data are for testing purposes only and can be adjusted according to your needs in actual use.