AWS Labs Synthetic Data MCP Server

1.0.15 verified Fri May 01 auth: no python

An AWS Labs Model Context Protocol (MCP) server for generating synthetic data. Currently at version 1.0.15, released on PyPI. Active development with periodic releases.

pip install awslabs-syntheticdata-mcp-server

Common errors

error ModuleNotFoundError: No module named 'syntheticdata_mcp_server' ↓

cause Using hyphens in import instead of underscores.

fix

Use 'from awslabs_syntheticdata_mcp_server import ...'

error botocore.exceptions.NoCredentialsError: Unable to locate credentials ↓

cause AWS credentials not configured.

fix

Set AWS_ACCESS_KEY_ID and AWS_SECRET_ACCESS_KEY environment variables, or configure ~/.aws/credentials.

Warnings

gotcha The package import name uses underscores (awslabs_syntheticdata_mcp_server) not hyphens. Using hyphens will cause ModuleNotFoundError. ↓

fix Replace hyphens with underscores in import statements.

breaking Requires Python >=3.10. Using older Python versions will fail installation. ↓

fix Upgrade Python to 3.10 or later.

gotcha AWS credentials must be configured via environment variables (AWS_ACCESS_KEY_ID, AWS_SECRET_ACCESS_KEY) or IAM role. The server will fail at runtime if no credentials are found. ↓

fix Ensure valid AWS credentials are set in the environment or use an IAM role when running on AWS.

Imports

SyntheticDataServer

wrong

from syntheticdata_mcp_server import SyntheticDataServer

correct

from awslabs_syntheticdata_mcp_server import SyntheticDataServer

Package name uses underscores, not hyphens.

Quickstart

Basic usage to generate synthetic data using the MCP server.

import os
from awslabs_syntheticdata_mcp_server import SyntheticDataServer

# Initialize server (uses AWS credentials from environment)
server = SyntheticDataServer()

# Example: generate synthetic data
prompt = "Generate a CSV with 10 rows of customer data including name, email, and age"
result = server.generate(prompt=prompt)
print(result)