home / mcp / amazon dynamodb mcp server

Amazon DynamoDB MCP Server

This read-only MCP Server allows you to connect to Amazon DynamoDB data from Claude Desktop through CData JDBC Drivers. For full CRUD support, check out the first managed MCP platform: CData Connect AI (https://www.cdata.com/ai/).

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "cdatasoftware-amazon-dynamodb-mcp-server-by-cdata": {
      "command": "java",
      "args": [
        "-jar",
        "/PATH/TO/CDataMCP-jar-with-dependencies.jar",
        "/PATH/TO/amazon-dynamodb.prp"
      ]
    }
  }
}

You run a local MCP server that exposes live Amazon DynamoDB data through a simple MCP interface. This lets you ask natural‑language questions and get up‑to‑date results from DynamoDB without writing SQL, while keeping data access self‑contained on your machine.

How to use

After you have the MCP server running, you use an MCP client to interact with it. You don’t need to write SQL queries; you simply request data and the client invokes the available tools under the hood. The server exposes read‑only access to DynamoDB data via the CData JDBC Driver, so you can retrieve tables, inspect columns, and run queries that return results in a structured format (CSV with headers for tables/columns, and standard result sets for queries). Typical usage patterns include asking questions like what is the schema of a table, which records match a given condition, or retrieving a subset of rows from a table.

How to install

# Prerequisites
- Java (JRE/JDK) 8+ installed and available on your PATH
- Maven for building the MCP server
- A local folder to host the JDBC driver and configuration files

# 1) Build the MCP server
mvn clean install

# 2) Prepare the JDBC driver (example file names shown; adjust paths to your environment)
# You will typically download and install the CData JDBC Driver for Amazon DynamoDB from CData

# 3) Create the JDBC connection properties file (amazon-dynamodb.prp) in your project folder
# Example contents are provided in the setup guide and should be adapted to your environment

# 4) Run the MCP server with your .prp file
java -jar /PATH/TO/CDataMCP-jar-with-dependencies.jar /PATH/TO/amazon-dynamodb.prp

Additional notes

This MCP server runs locally and is read‑only by design. It exposes a simple command interface that maps to the underlying JDBC driver’s data model, enabling you to explore tables, columns, and data via the MCP client without writing SQL. If you need write, update, delete, or action capabilities, use the full MCP server option from CData that supports those operations.

Available tools

amazondynamodb_get_tables

Retrieves the list of tables available in the DynamoDB data source. Output is CSV with the first line as column headers.

amazondynamodb_get_columns

Retrieves the list of columns for a specified table. Output is CSV with column headers on the first line.

amazondynamodb_run_query

Executes a SQL SELECT query against the configured data source and returns the resulting rows.