PostgreSQL-DynamoDB MCP Server

A Model Context Protocol (MCP) server that provides tools to help customers use Amazon DynamoDB as if it were PostgreSQL. This server translates PostgreSQL-style operations into DynamoDB operations, making it easier for developers familiar with relational databases to work with DynamoDB.

Features

• PostgreSQL-like Interface: Use familiar SQL-style operations with DynamoDB
• Table Management: Create tables with PostgreSQL-style schema definitions
• CRUD Operations: Insert, select, update, and delete records using intuitive commands
• Schema Inspection: Describe tables and their structure
• AWS Integration: Seamless integration with AWS DynamoDB service

Available Tools

create_table

Create a DynamoDB table with PostgreSQL-like schema definition.

Parameters:

• table_name: Name of the table to create
• columns: Array of column definitions with name, type, and key properties

insert_record

Insert a record into a DynamoDB table (equivalent to PostgreSQL INSERT).

Parameters:

• table_name: Target table name
• data: Key-value pairs representing the record to insert

select_records

Query records from a DynamoDB table (equivalent to PostgreSQL SELECT).

Parameters:

• table_name: Source table name
• key_condition: Primary key condition for querying
• filter_expression: Optional filter for additional conditions
• limit: Maximum number of records to return

update_record

Update an existing record in a DynamoDB table (equivalent to PostgreSQL UPDATE).

Parameters:

• table_name: Target table name
• key: Primary key of the record to update
• updates: Fields and values to update

delete_record

Delete a record from a DynamoDB table (equivalent to PostgreSQL DELETE).

Parameters:

• table_name: Target table name
• key: Primary key of the record to delete

describe_table

Get detailed information about a table's schema and properties (equivalent to PostgreSQL \d).

Parameters:

• table_name: Name of the table to describe

Installation

1. Install dependencies:

pip install -r requirements.txt

2. Configure AWS credentials:

aws configure

Usage

Run the MCP server:

python server.py

The server will start and listen for MCP protocol messages via stdio.

Configuration

Ensure your AWS credentials are properly configured with permissions to:

• Create DynamoDB tables
• Read/write DynamoDB items
• Describe DynamoDB tables

Example Usage

Creating a Table

{
  "table_name": "users",
  "columns": [
    {"name": "user_id", "type": "string", "primary_key": true},
    {"name": "email", "type": "string"},
    {"name": "created_at", "type": "string", "sort_key": true}
  ]
}

Inserting Data

{
  "table_name": "users",
  "data": {
    "user_id": "123",
    "email": "user@example.com",
    "created_at": "2024-01-01T00:00:00Z"
  }
}

Querying Data

{
  "table_name": "users",
  "key_condition": {"user_id": "123"},
  "limit": 10
}

Benefits

• Familiar Interface: Use PostgreSQL-style operations with DynamoDB
• Reduced Learning Curve: Easier transition from relational to NoSQL databases
• MCP Integration: Works seamlessly with MCP-compatible AI assistants and tools
• AWS Native: Built specifically for Amazon DynamoDB with best practices

License

MIT License