adp_get_tablesLABSCO SUMMARY
Read-only by construction, and that is the safe version.
The query tool executes SELECT and nothing else, which is the right default for payroll and HR data. CData points elsewhere for anything more: their downloadable MCP server for full read-write-update-delete with a simpler setup, and CData Connect AI for a managed remote endpoint. The setup here is the honest cost — a licensed JDBC driver, a Maven build and a hand-written properties file — but if ADP already sits behind a CData driver in your stack, this reuses that connection rather than adding another integration.
What it is
A local, read-only MCP server from CData that wraps their JDBC driver for ADP. The driver presents ADP as relational SQL models; the server exposes three tools over that, so a model can discover the schema and run SELECT queries without anyone writing SQL by hand.
What you get
adp_get_tables— the tables available in the data source, returned as CSV with a header rowadp_get_columns— the columns on a named table, same CSV shape, so the model can check field names before queryingadp_run_query— executes a SQL SELECT query against ADP- A
Tablessetting that only picks which tables also get a ready-made description (blank means none); it does not limit what the tools can list or query, so limit the connection or the account it signs in with
Requirements
The CData JDBC Driver for ADP, downloaded separately and licensed — run java -jar cdata.jdbc.adp.jar --license and enter your name, email and either TRIAL or a licence key. Java to run the server and Maven to build it: mvn clean install produces CDataMCP-jar-with-dependencies.jar. Then write a .prp file naming Prefix, ServerName, ServerVersion, DriverPath, DriverClass (cdata.jdbc.adp.ADPDriver), the JdbcUrl built with the driver's connection-string utility, and Tables. The client launches java with the jar and the .prp path as arguments. Transport is stdio, so the server must run on the same machine as the client. MIT licensed.
Setup effort
Build from source — git clone https://github.com/cdatasoftware/adp-mcp-server-by-cdata.git
USE CASES
01
Answering an HR question without an export
Ask in plain language and let the model discover the tables, check the columns and run the SELECT itself.
02
Finding out what ADP actually exposes
List the tables and inspect the columns on the ones that look relevant before writing any query.
03
Limiting what a model can reach
Name only the permitted tables in the properties file so nothing outside that set is queryable.
3 tools
Listed in project docs. Your client may show a different list.
adp_get_columnsadp_run_queryBEFORE YOU INSTALL
What to know first
Tools you get
3 tools named in the project's documentation. Tool names start with the Prefix in your .prp file, so the README's Prefix=adp gives adp_get_tables. All three only read (run_query executes SELECT), even though the README's usage section says the tools can write, update and delete.
Where it runs
Both documented setups run the server on your machine.
INSTALLATION
Connect your client
You clone and build this one yourself.
Server setup
TERMINAL
git clone https://github.com/cdatasoftware/adp-mcp-server-by-cdata.git
cd adp-mcp-server-by-cdata
mvn clean installDownload and install the CData JDBC Driver for ADP from https://www.cdata.com/drivers/adp/download/jdbc
License the driver: from the driver install's lib folder run java -jar cdata.jdbc.adp.jar --license, then enter your name, email, and "TRIAL" (or your license key)
Build the connection string: run java -jar cdata.jdbc.adp.jar to open the Connection String utility, click "Test Connection" (browser OAuth if the source needs it), and copy the connection string
Create adp.prp with:
FILE · adp.prp
Prefix=adp
ServerName=CDataADP
ServerVersion=1.0
DriverPath=<YOUR_DRIVER_PATH>
DriverClass=cdata.jdbc.adp.ADPDriver
JdbcUrl=<YOUR_JDBC_URL>
Tables=Tables only picks which tables also get a ready-made description for your assistant, and empty means none; the server can still list and query every table your connection string reaches, so to keep data out of reach, limit that connection or the account it signs in with.
Add the mcpServers entry (block below) to claude_desktop_config.json, then fully quit and re-open the client
MCP Clients
Claude Desktop — Windows, macOS or Linux
JSON
{
"mcpServers": {
"adp": {
"command": "<YOUR_PATH_TO_JAVA>",
"args": [
"-jar",
"<YOUR_PATH_TO_CDATA_MCP_JAR_WITH>",
"<YOUR_PATH_TO_ADP>"
]
}
}
}