Amazon S3

This read-only MCP Server allows you to connect to Amazon S3 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/).

java

GitHub Stars

java

Language

7 months ago

First Indexed

3 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "cdatasoftware-amazon-s3-mcp-server-by-cdata": {
      "command": "java",
      "args": [
        "-jar",
        "CDataMCP-jar-with-dependencies.jar",
        "/PATH/TO/amazon-s3.prp"
      ]
    }
  }
}

You can query live data from Amazon S3 using a dedicated MCP server that exposes S3 data through a simple, read-only MCP interface. This lets you ask natural language questions and get up-to-date results from your S3 data without writing SQL. The server runs locally and reads data through the CData JDBC Driver for Amazon S3, wrapping it in MCP tools for easy AI-assisted data access.

How to use

You will run the MCP server locally and connect an MCP client, such as Claude Desktop, to the server using a standard config. Once connected, you can ask questions like “What is the latest order total in bucket X?” or “Show me objects uploaded this month in folder Y.” The server exposes a small set of tools that let the AI client discover which tables (data sources) exist, inspect their columns, and run read-only queries to retrieve information. No SQL writing is required for typical questions.

Practical usage patterns include: saying what you want to know, letting the AI client discover available data, and then requesting specific views or aggregates. If you need a list of tables, ask for {servername}_get_tables. If you need details about a table’s structure, ask for {servername}_get_columns. To retrieve data, ask for {servername}_run_query with a SELECT-like query that the MCP server translates into its underlying data access.

How to install

Prerequisites you’ll need before starting: Java installed on your machine, and Maven for building the MCP server.

# 1) Clone the project
git clone https://github.com/cdatasoftware/amazon-s3-mcp-server-by-cdata.git
cd amazon-s3-mcp-server-by-cdata

# 2) Build the server
mvn clean install

# The build creates CDataMCP-jar-with-dependencies.jar

Install and license the CData JDBC Driver for Amazon S3. Follow the driver’s license steps to activate it locally on your machine, then configure the driver using the provided connection utilities.
Create a .prp file with your JDBC connection details, using the required properties such as Prefix, ServerName, ServerVersion, DriverPath, DriverClass, JdbcUrl, and Tables. This file wires your JDBC data source to the MCP server.
Run the MCP server using the java command and your .prp file to start the service. The example below shows running the server on its own with a local PRP, which in practice would point to your generated amazon-s3.prp.

java -jar /PATH/TO/CDataMCP-jar-with-dependencies.jar /PATH/TO/amazon-s3.prp

Note: This server is intended for local, read-only access and uses stdio, so it can work with clients running on the same machine.

## Additional setup and notes

Configure your Claude Desktop (or another MCP client) to load the new MCP server by adding an entry that points to the local Java process and the PRP you created. After configuring, restart the client to ensure the MCP server appears in your available servers.

If the client does not immediately show the MCP server, fully quit the client and relaunch it to refresh the list of available MCP servers.

## Available tools

### amazons3\_get\_tables

Retrieves a list of tables (data sources) available in the data source. Returns CSV output where the first line contains column headers.

### amazons3\_get\_columns

Retrieves a list of columns for a specified table. Returns CSV output with column headers as the first line.

### amazons3\_run\_query

Executes a SQL-like SELECT query against the configured data source and returns the results.

Built by

VeilStrat

AI signals for GTM teams