home / mcp / adp mcp server

ADP MCP Server

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

You run a local MCP server that exposes ADP data via a simple, read‑only interface. This lets you ask natural‑language questions and receive live data from ADP without writing SQL, using your preferred MCP client on the same machine.

How to use

Start the MCP server on your machine and connect your MCP client to it. You will use the built server as a local data access layer for ADP, enabling you to read live data and answer questions such as opportunities, tickets, or calendar events without writing SQL.

How to install

Prerequisites: Java Runtime Environment (JRE) or Java Development Kit (JDK) installed on your machine.

1. Build the MCP server package.

mvn clean install

This creates the MCP server jar named CDataMCP-jar-with-dependencies.jar.

2. Install the CData JDBC Driver for ADP and license it (this enables the ADP data source connection). Follow these steps on your system: - Download the driver from the CData site. - Run the license command from the driver’s lib directory to license the driver. - Command: java -jar cdata.jdbc.adp.jar --license - Enter your name, email, and TRIAL (or your license key).

3. Configure the JDBC connection string for ADP and generate the connection string you will reuse in the MCP setup: - Run: java -jar cdata.jdbc.adp.jar - Use the Connection String utility to build a connection string and test it. - Copy the resulting JDBC URL for later use.

4. Create a .prp file describing your JDBC connection (for example adp.prp) with the following properties: ``Prefix=adp ServerName=CDataADP ServerVersion=1.0 DriverPath=PATH\\TO\\cdata.jdbc.adp.jar DriverClass=cdata.jdbc.adp.ADPDriver JdbcUrl=jdbc:adp:InitiateOAuth=GETANDREFRESH; Tables=`` Replace PATH\\TO\\cdata.jdbc.adp.jar with the full path to your driver jar and fill in your actual JdbcUrl.

Additional configuration and usage notes

The MCP server runs locally in stdio mode, meaning it communicates with clients on the same machine. You start it with Java and point it at your adp.prp file.

5. Run the MCP server on its own using the prepared .prp file: ``java -jar /PATH/TO/CDataMCP-jar-with-dependencies.jar /PATH/TO/adp.prp`` Note: The server is designed for local use and works with MCP clients that run on the same machine.

Claude Desktop integration example

To add the MCP server to Claude Desktop, create or update a Claude configuration file (claude_desktop_config.json) with an entry that launches the MCP server jar and passes your adp.prp file.

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

Troubleshooting

If the MCP server does not appear in Claude Desktop, fully quit Claude Desktop and relaunch it so the server becomes visible.

If Claude Desktop cannot retrieve data, verify your connection string is correct and that adp.prp references a valid JdbcUrl. Rebuild and restart the MCP server if needed.

If you experience connection issues, contact CData Support or ask the CData Community for guidance.

License

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

Available tools

adp_get_tables

Retrieves a list of tables available in the data source; output is in CSV format with the first line as column headers.

adp_get_columns

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

adp_run_query

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