home / mcp / sage-300 mcp server

sage-300 MCP Server

This read-only MCP Server allows you to connect to Sage 300 data from Claude Desktop through CData JDBC Drivers. For full CRUD support, check out our MCP Server for Sage 300 (https://www.cdata.com/drivers/sage300/download/mcp).

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "cdatasoftware-sage-300-mcp-server-by-cdata": {
      "command": "java",
      "args": [
        "-jar",
        "/PATH/TO/CDataMCP-jar-with-dependencies.jar",
        "/PATH/TO/Salesforce.prp"
      ]
    }
  }
}

You can query live Sage 300 data through a dedicated MCP server that wraps the CData JDBC Driver. This read-only MCP server lets AI clients retrieve up-to-date information from Sage 300 without writing SQL, using a straightforward MCP interface.

How to use

Once your MCP server is running, you can ask your AI client (such as Claude Desktop) to retrieve data, answer questions, and explore Sage 300 information in natural language. You can request lists of tables, inspect columns for a chosen table, or run read-only queries to retrieve data. The server exposes standard tools that translate your natural language requests into data access actions, so you don’t need to write SQL.

How to install

Prerequisites you need before installing and running the server.

# Install Java Development Kit (JDK) and Maven
# Ensure java and mvn are on your PATH
java -version
mvn -version

1) Clone the project and navigate into the directory.

git clone https://github.com/cdatasoftware/sage-300-mcp-server-by-cdata.git
cd sage-300-mcp-server-by-cdata

2) Build the server to produce the runnable JAR.

mvn clean install

3) Install the CData JDBC Driver for Sage 300. Download from the CData site and install according to the driver installation instructions for your OS.

4) License the CData JDBC Driver. Open the driver’s lib directory and run the license command, then provide your name, email, and license key.

# Example (Windows/Linux/macOS paths shown for illustration; adapt to your environment)
java -jar cdata.jdbc.sage300.jar --license

Additional setup and configuration

5) Configure the JDBC connection to Sage 300. Run the connection string utility from the same folder as the driver to test and copy the connection string for later use.

java -jar cdata.jdbc.sage300.jar
# Configure connection and Test Connection
# Copy the resulting JDBC URL for use in the next step

Create the MCP properties file

Create a properties file (for example sage-300.prp) with the following properties. Replace the placeholder values with your actual paths and connection string.

env
Prefix=sage300
ServerName=CDataSage300
ServerVersion=1.0
DriverPath=PATH\TO\cdata.jdbc.sage300.jar
DriverClass=cdata.jdbc.sage300.Sage300Driver
JdbcUrl=jdbc:sage300:InitiateOAuth=GETANDREFRESH;
Tables=

Running the MCP server

Start the MCP server on its own process. The server runs in stdio mode, so it’s designed to be used by clients on the same machine.

java -jar /PATH/TO/CDataMCP-jar-with-dependencies.jar /PATH/TO/sage-300.prp

Available tools

sage300_mcp_get_tables

Retrieves a list of tables available in the Sage 300 data source. Output is in CSV format with column headers on the first line.

sage300_mcp_get_columns

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

sage300_mcp_run_query

Executes a SQL SELECT query against the Sage 300 data source and returns the results.