home / mcp / highrise mcp server

Highrise MCP Server

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

Installation
Add the following to your MCP client configuration file.

Configuration

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

You set up a read-only MCP server that exposes live Highrise data to large language models through an MCP interface. This lets you ask natural-language questions and receive up-to-date results from Highrise without writing SQL. The server runs locally and uses the CData JDBC Driver under the hood to connect Highrise as relational data.

How to use

Once the MCP server is running on your machine, connect an MCP client (such as Claude Desktop) to the local stdio endpoint. You can then ask questions like “What is the total number of open tickets in the SUPPORT project?” or “Show me recent Highrise calendar events.” The built-in tools will read data from Highrise, perform the necessary queries, and return results in a natural-language response. You do not need to call specific tools manually; simply ask your client to retrieve or summarize data and rely on the server to translate your query into the underlying data operations.

How to install

Prerequisites: Java installed on your system and a working Java runtime in your PATH.

# 1. Clone the MCP server project
git clone https://github.com/cdatasoftware/highrise-mcp-server-by-cdata.git
cd highrise-mcp-server-by-cdata

# 2. Build the MCP server JAR
mvn clean install
# This produces CDataMCP-jar-with-dependencies.jar

# 3. Install the CData JDBC Driver for Highrise
# Download and install from:
# https://www.cdata.com/drivers/highrise/download/jdbc

# 4. License the JDBC Driver
# For Windows
# java -jar cdata.jdbc.highrise.jar --license
# For Mac/Linux, run in the same directory as the driver JAR
# Enter your name, email, and a license key or TRIAL

# 5. Configure your connection to Highrise
# Open the Connection String utility to test and copy the JDBC URL
# Run this in the same directory as the JAR
java -jar cdata.jdbc.highrise.jar
# Test connection and copy the connection string

# 6. Create a .prp file for the JDBC connection (example highrise.prp)
# Use the properties below, updating paths as needed

Prefix=highrise
ServerName=CDataHighrise
ServerVersion=1.0
DriverPath=PATH\\TO\\cdata.jdbc.highrise.jar
DriverClass=cdata.jdbc.highrise.HighriseDriver
JdbcUrl=jdbc:highrise:InitiateOAuth=GETANDREFRESH;
Tables=

Additional setup tips

After you have the highrise.prp ready, start the MCP server with the following command. The server runs via stdio, so you’ll interact with it on the same machine using an MCP client.

java -jar CDataMCP-jar-with-dependencies.jar /PATH/TO/highrise.prp

Notes on running and maintenance

The MCP server operates in read-only mode by default. If you require full read, write, update, and delete capabilities, you would need a different MCP server configuration that supports those operations.

Troubleshooting

If you cannot see the MCP server in your client, ensure you have fully exited and restarted the client after starting the server. If the client cannot retrieve data, verify that the Highrise JDBC connection string is correct and that the driver is licensed and accessible from the machine running the MCP server.

License

This MCP server is provided under the MIT License. You may use, modify, and distribute it in compliance with that license.

Available tools

highrise_get_tables

Retrieves a list of tables available in Highrise data source. Output is CSV with headers on the first line.

highrise_get_columns

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

highrise_run_query

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