home / mcp / blackbaud fe nxt mcp server
This read-only MCP Server allows you to connect to Blackbaud FE NXT 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/).
Configuration
View docs{
"mcpServers": {
"cdatasoftware-blackbaud-fe-nxt-mcp-server-by-cdata": {
"command": "java",
"args": [
"-jar",
"/PATH/TO/CDataMCP-jar-with-dependencies.jar",
"/PATH/TO/blackbaud-fe-nxt.prp"
]
}
}
}You run a local MCP server that exposes Blackbaud FE NXT data to language models through a simple, read-only MCP interface. This enables you to ask natural language questions and receive live data answers without writing SQL. The server wraps the CData JDBC Driver to present Blackbaud FE NXT data as relational models that your MCP client can query.
Once your MCP server is running, you connect to it from your MCP client (for example Claude Desktop) and begin asking questions about your Blackbaud FE NXT data. You won’t need to write SQL; the client uses built-in tools to explore the data, read results, and ask questions like “What is the open opportunities value by region?” or “Show me today’s calendar events.” The client automatically handles data retrieval through the exposed MCP server endpoints. If you already have a configured MCP server, simply start interacting with it in the same way you would with other MCP sources.
Follow these concrete steps to install and run the MCP server locally.
# 1) Clone the repository
git clone https://github.com/cdatasoftware/blackbaud-fe-nxt-mcp-server-by-cdata.git
cd blackbaud-fe-nxt-mcp-server-by-cdata
# 2) Build the server
mvn clean install
# This creates the JAR file: CDataMCP-jar-with-dependencies.jar3) Download and install the CData JDBC Driver for Blackbaud FE NXT. This can be found on the CData website under JDBC drivers for Blackbaud FE NXT. 4) License the CData JDBC Driver. Locate the lib folder in the installation directory, then run the license command and provide your name, email, and a license key (TRIAL or your key). 5) Configure your connection to the data source (example uses Salesforce format). Run the connection utility to generate and test a connection string, then copy it for use in your configuration file.
# Example: open the Connection String utility (driver jar)
java -jar cdata.jdbc.blackbaudnxt.jar6) Create a .prp file for your JDBC connection (example name: blackbaud-fe-nxt.prp) with the following properties. This file tells the MCP server how to reach your data source.
# blackbaud-fe-nxt.prp
Prefix=blackbaudnxt
ServerName=CDataBlackBaudNXT
ServerVersion=1.0
DriverPath=PATH\TO\cdata.jdbc.blackbaudnxt.jar
DriverClass=cdata.jdbc.blackbaudnxt.BlackBaudNXTDriver
JdbcUrl=jdbc:blackbaudnxt:InitiateOAuth=GETANDREFRESH;
Tables=Prepare Claude Desktop or your chosen MCP client by adding a config entry that points to the MCP server JAR and the .prp file. The client will invoke the server using an inline Java command to run the MCP JAR with your .prp file. This enables the client to access the exposed MCP tools and perform queries.
To start the MCP server locally, run the following command. The server runs in stdio mode, so you’ll interact with it from the same machine.
java -jar /PATH/TO/CDataMCP-jar-with-dependencies.jar /PATH/TO/blackbaud-fe-nxt.prpAfter the server starts, you can use your MCP client to call built-in tools that read from the connected data source. You can list available tables, inspect columns, and run SQL SELECT queries through the MCP interface. The tools are designed to let you explore the data model without writing SQL directly in your queries.
If you encounter issues, try the following steps. Fully quit and restart your MCP client to ensure it detects new or updated MCP servers. Verify your connection string is correct and test it in the driver’s connection utility. If problems persist, contact CData Support or join the CData Community for help.
This MCP server is built to work with a licensed CData JDBC Driver. Ensure you license the driver in your environment before running the server.
Retrieves a list of tables available in the data source. Output is CSV with column headers in the first line.
Retrieves a list of columns for a specific table. Output is CSV with column headers in the first line.
Executes a SQL SELECT query against the data source and returns the results.