home / mcp / enterprisedb mcp server

EnterpriseDB MCP Server

Reads live EnterpriseDB data via the CData JDBC Driver and exposes it through an MCP interface for querying by AI clients.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

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

You can query live EnterpriseDB data through a read-only MCP server that wraps the CData JDBC Driver for EnterpriseDB. This enables AI clients to ask natural language questions and receive live data without writing SQL. The server exposes a simple MCP interface and is designed for read-only access to EnterpriseDB data sources.

How to use

After you start the MCP server, you will interact with it through your MCP client. You do not need to write SQL; ask questions like: “What is the current revenue by region?” or “Show me open tickets in the SUPPORT project.” The server exposes a set of tools behind the scenes and handles data retrieval automatically, returning results that your client can display or reason about.

How to install

Prerequisites you need before installing: a Java Runtime Environment (JRE) compatible with the MCP server, and access to create the JDBC connection file using the CData JDBC Driver for EnterpriseDB.

Step 1. Build the MCP server JAR from sources.

mvn clean install

Step 2. Prepare the EnterpriseDB JDBC driver as part of the MCP setup. Install and license the driver following the standard flow, then generate a connection properties file (enterprisedb.prp) that points to your EnterpriseDB instance.

Step 3. Create the MCP startup command using the generated properties file. You will run the MCP server from Java with the prepared .prp file.

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

Additional setup notes

The MCP server runs in stdio mode, so it is intended to be used with clients running on the same machine. Ensure you have closed all instances of the MCP client and restarted them if the MCP server does not appear.

Notes on configuration and usage

The setup process includes configuring a connection string for EnterpriseDB and placing a .prp file in the expected location. You typically reference the .prp file when starting the MCP server so that the server knows how to connect to EnterpriseDB.

Troubleshooting

If you have trouble seeing the MCP server in your client or data retrieval fails, ensure you fully restart the MCP client after starting the server. Verify the EnterpriseDB connection string and the path to the JDBC driver are correct, then test the connection string and update the .prp file if needed.

Tools and endpoints overview

The MCP server provides internal tools to discover and query the data source. You can retrieve available tables, list columns for a table, and run a SELECT query. These tools drive the data access behind the scenes and return results to your AI client.

Available tools

enterprisedb_get_tables

Retrieves a list of available tables in the EnterpriseDB data source. The output is provided in CSV format with the first line containing column headers.

enterprisedb_get_columns

Retrieves a list of columns for a specific table. The output is provided in CSV format with the first line containing column headers.

enterprisedb_run_query

Executes a SQL SELECT query against the EnterpriseDB data source and returns the results.