home / mcp / greenplum mcp server

Greenplum MCP Server

This read-only MCP Server allows you to connect to Greenplum 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-greenplum-mcp-server-by-cdata": {
      "command": "java",
      "args": [
        "-jar",
        "/PATH/TO/CDataMCP-jar-with-dependencies.jar",
        "/PATH/TO/greenplum.prp"
      ]
    }
  }
}

You can query live Greenplum data through a local, read-only MCP server that wraps the CData JDBC Driver. This enables natural language questions to retrieve up-to-date information from Greenplum without writing SQL, while keeping data access secure and centralized on your machine.

How to use

Once the MCP server is running on your machine, you connect your MCP client (such as Claude Desktop) to the local server. You can then ask questions about your Greenplum data in natural language, and the AI client will fetch live results via the MCP tools. Typical tasks include discovering available tables, listing columns in a table, and running read-only queries to retrieve data. Use conversational prompts like asking for data summaries, counts, or correlations across related tables.

How to install

Prerequisites you need before starting: Java Runtime Environment (JRE) or JDK installed, and Maven available for building the MCP server. You will also need the CData JDBC Driver for Greenplum installed and licensed.

# 1) Clone the MCP server repository
git clone https://github.com/cdatasoftware/greenplum-mcp-server-by-cdata.git
cd greenplum-mcp-server-by-cdata

# 2) Build the MCP server
mvn clean install

# This creates the JAR file: CDataMCP-jar-with-dependencies.jar

Configure data source and run the server

Obtain and license the CData JDBC Driver for Greenplum, then configure a connection to Greenplum. You will create a .prp file that describes the JDBC connection. The final step is to start the MCP server using the generated JAR and your .prp file.

# Install the CData JDBC Driver for Greenplum (follow the driver's installer steps for your OS)

# License the driver (example path shown for illustration):
# Windows: C:\Program Files\CData\CData JDBC Driver for Greenplum\
# Mac/Linux: /Applications/CData JDBC Driver for Greenplum/

java -jar cdata.jdbc.greenplum.jar --license

# Configure the connection string (interactive utility):
java -jar cdata.jdbc.greenplum.jar
# Copy the produced connection string for use in the .prp file

Create the MCP property file for Greenplum

Create a .prp file (for example greenplum.prp) with the following properties to expose the Greenplum data through MCP.

Prefix=greenplum
ServerName=CDataGreenplum
ServerVersion=1.0
DriverPath=PATH\TO\cdata.jdbc.greenplum.jar
DriverClass=cdata.jdbc.greenplum.GreenplumDriver
JdbcUrl=jdbc:greenplum:InitiateOAuth=GETANDREFRESH;
Tables=

Configure Claude Desktop (optional client)

If you use Claude Desktop to access the MCP server, prepare a configuration file (claude_desktop_config.json) that adds the MCP server entry. This file is placed in the appropriate Claude configuration directory on your system.

{
  "mcpServers": {
    "greenplum_mcp": {
      "command": "PATH\\TO\\java.exe",
      "args": [
        "-jar",
        "PATH\\TO\\CDataMCP-jar-with-dependencies.jar",
        "PATH\\TO\\greenplum.prp"
      ]
    }
  }
}

Running the server

Start the MCP server by running the Java application with your MCP property file. The server runs locally on the same machine as Claude Desktop or your MCP client.

java -jar /PATH/TO/CDataMCP-jar-with-dependencies.jar /PATH/TO/greenplum.prp

Usage details and tools

After configuration, you will have access to built-in tools that let you read data from Greenplum. You typically do not call the tools directly; instead, you ask your AI client to query the data and it will use the available tools behind the scenes.

Troubleshooting

If you cannot see the MCP server in your client, ensure you have fully restarted the client after starting the server. If your client cannot retrieve data, verify the .prp connection string and restart the client to apply changes. For further assistance, contact CData Support or join the CData Community.

License

This MCP server is licensed under the MIT License. You may use, modify, and distribute it in accordance with the MIT terms.

Tools and endpoints

The MCP server exposes the following read-only tools for interacting with Greenplum data. Use these to discover data structure and retrieve information without writing SQL.

Tools list

- greenplum_get_tables: Retrieves a list of tables available in the Greenplum data source. The output is in CSV format with column headers.

- greenplum_get_columns: Retrieves a list of columns for a given table. The output is in CSV format with column headers.

- greenplum_run_query: Executes a SQL SELECT query against Greenplum.

JSON-RPC request examples

If you are scripting requests instead of using a client, you can call the tools using the following structure. Replace the tool name and arguments as needed.

Examples of usage in practice

Ask questions like: What is the correlation between closed won opportunities and account industry? How many open tickets exist in the SUPPORT project? What calendar events do I have today? The AI client will use the available MCP tools to fetch the required data from Greenplum.

Available tools

greenplum_get_tables

Retrieves the list of tables available in Greenplum with the output in CSV format including headers.

greenplum_get_columns

Retrieves the list of columns for a specified table in CSV format with headers.

greenplum_run_query

Executes a SQL SELECT query against Greenplum and returns the results.