home / mcp / greenhouse mcp server

Greenhouse MCP Server

Provides live Greenhouse data through a read-only MCP interface via the CData JDBC Driver.

Installation

Add the following to your MCP client configuration file.

Configuration

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

This read-only MCP server lets you query live Greenhouse data through the CData JDBC Driver without writing SQL. It exposes Greenhouse data as MCP tools so you can ask questions in natural language and retrieve current results directly from Greenhouse. This makes it easy to integrate live data into your AI workflows while keeping data access safe and read-only.

How to use

You will run the MCP server locally on the same machine as your AI client. Start the server with the Java runtime and point it to your prepared.prp connection descriptor. Once running, your MCP client can call the built-in tools to list tables, inspect columns, and run read-only queries against Greenhouse data. Use natural language prompts to ask questions like what is the latest status of opportunities, which accounts have open tickets, or what events are scheduled today.

How to install

Prerequisites you need before installation:

Install Java (JDK 8+ required) and a Java runtime environment that can execute the MCP server JAR.

Install Maven to build the MCP server (optional if you use a pre-built JAR).

Step-by-step commands you should run in order:

Clone the project repository and enter the directory.

Build the server to generate the MCP JAR with dependencies.

Download and install the CData JDBC Driver for Greenhouse from the official source and license it as required.

Create a JDBC connection descriptor file (greenhouse.prp) with your driver path, JDBC URL, and table access configuration as shown in the setup outline.

Run the server and connect your client

Run the MCP server on the host machine. Use the standard Java invocation and point to your .prp file.

Available tools

greenhouse_get_tables

Retrieves a list of tables available in Greenhouse. The output is returned in CSV format with headers in the first line.

greenhouse_get_columns

Retrieves a list of columns for a specified table. The output is returned in CSV format with headers in the first line.

greenhouse_run_query

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