home / mcp / epicor kinetic mcp server

Epicor Kinetic MCP Server

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

You can run a local, read-only MCP server that exposes Epicor Kinetic data via the MCP interface. It lets you ask natural language questions and receive live data from Epicor Kinetic without writing SQL, while keeping changes restricted to a read-only view for safety.

How to use

Once the MCP server is running, you interact with it through an MCP client. You can ask questions like “What is the current status of open opportunities in Epicor Kinetic?” or “Show me recent activities across the Epicor Kinetic modules.” The server translates your requests into the underlying data model exposed by the CData JDBC Driver for Epicor Kinetic, retrieves live data, and returns structured results. You don’t need to write SQL queries; you simply request the information you need in natural language.

How to install

Prerequisites you need before installation:

• Java Development Kit (JDK) 8 or newer • Maven for building the server • A CData JDBC Driver for Epicor Kinetic (downloaded and licensed)

Step-by-step commands you will run:

git clone https://github.com/cdatasoftware/epicor-kinetic-mcp-server-by-cdata.git
cd epicor-kinetic-mcp-server-by-cdata

mvn clean install

Additional configuration and run details

After building the server, you will set up the CData JDBC Driver for Epicor Kinetic, license it, and create a properties file that points the MCP server to your data source. Then you start the MCP server using the Java runtime with the path to your .prp configuration.

Key steps you will perform in sequence (as shown in the setup guide):

# Build the MCP server jar (already completed by the mvn install step)
# Download and install the CData JDBC Driver for Epicor Kinetic from the CData site

# License the driver (example path shown for Windows/Mac/Linux):
# Windows:  java -jar cdata.jdbc.epicorkinetic.jar --license
# Mac/Linux:    java -jar cdata.jdbc.epicorkinetic.jar --license

# Configure a connection string using the driver’s Connection String utility
# Example interaction (output shown here is representative, follow in your environment):
# java -jar cdata.jdbc.epicorkinetic.jar
# Then test the connection and copy the JDBC URL

# Create a .prp file (epicor-kinetic.prp) with your connection details:
# Prefix=epicorkinetic
# ServerName=CDataEpicorKinetic
# ServerVersion=1.0
# DriverPath=PATH\TO\cdata.jdbc.epicorkinetic.jar
# DriverClass=cdata.jdbc.epicorkinetic.EpicorKineticDriver
# JdbcUrl=jdbc:epicorkinetic:InitiateOAuth=GETANDREFRESH;
# Tables=

# Start the MCP server (example from the run instructions):
# java -jar /PATH/TO/CDataMCP-jar-with-dependencies.jar /PATH/TO/Salesforce.prp

Troubleshooting and notes

If you cannot see or connect to the MCP Server, fully quit the MCP client you are using and restart it so the new server appears. Ensure the connection string in the .prp file is correct and tested via the JDBC Driver utility. If you run into issues, verify you licensed the driver and that the JDBC URL matches the source data configuration. If problems persist, contact CData Support or engage with the CData Community for further guidance.

Available tools

epicor_kinetic_get_tables

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

epicor_kinetic_get_columns

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

epicor_kinetic_run_query

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