home / mcp / zoho inventory mcp server

Zoho Inventory MCP Server

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

This MCP server provides a local, read-only interface to Zoho Inventory data through the CData MCP framework. It wraps the CData JDBC Driver for Zoho Inventory to expose live data via MCP tools, enabling you to ask natural language questions and have the AI retrieve up-to-date information without writing SQL. This is ideal for querying Zoho Inventory data from LLMs in a safe, read-only mode.

How to use

You run the MCP server locally and connect your AI client to it. The server exposes a small set of tools that let you discover which tables exist, inspect their columns, and execute read-only queries. You don’t need to write SQL unless you want to; you can simply ask questions like, “What are my open opportunities by account?” or “Show me current inventory levels by product.” The AI client will invoke the exposed tools behind the scenes to fetch data from Zoho Inventory through the JDBC driver.

To use the server in your workflow, run the MCP server process on your machine and configure your AI client to point at the local stdio-based server. The client will then use the built-in tools to read data from Zoho Inventory. Keep in mind this is read-only access in this setup, so write/update actions are not available here.

How to install

Prerequisites you need before installing this MCP server: a Java runtime environment, and Maven for building the project. You may also need the CData JDBC Driver for Zoho Inventory installed on your machine if you plan to connect through JDBC.

Step 1 — Clone the project and navigate to it.

git clone https://github.com/cdatasoftware/zoho-inventory-mcp-server-by-cdata.git
cd zoho-inventory-mcp-server-by-cdata

Step 2 — Build the server to produce the MCP JAR.

mvn clean install
```
This creates the JAR file: CDataMCP-jar-with-dependencies.jar

Step 3 — Install and license the CData JDBC Driver for Zoho Inventory.

# Download the driver from the producer's site, then install and license as instructed by the driver package.
# Example license step (location depends on your OS):
java -jar cdata.jdbc.zohoinventory.jar --license

Step 4 — Configure the JDBC connection and create a .prp file.

# Use the JDBC driver's connection utility to craft a connection string, then create zoho-inventory.prp with these properties:
Prefix=zohoinventory
ServerName=CDataZohoInventory
ServerVersion=1.0
DriverPath=PATH\TO\cdata.jdbc.zohoinventory.jar
DriverClass=cdata.jdbc.zohoinventory.ZohoInventoryDriver
JdbcUrl=jdbc:zohoinventory:InitiateOAuth=GETANDREFRESH;
Tables=

Step 5 — Run the MCP server locally using the generated .prp file.

java -jar /PATH/TO/CDataMCP-jar-with-dependencies.jar /PATH/TO/zoho-inventory.prp

Additional configuration notes

The server runs in stdio mode, which means it communicates with clients on the same machine. If you plan to connect from a separate client, you should use a remote MCP setup instead of stdio.

Example Claude Desktop configuration for a local stdio MCP server is shown in the following structure. You replace PATH and file names with your actual paths.

Troubleshooting and tips

If the MCP server does not appear in your AI client, ensure you have fully exited and restarted the client after starting the MCP process. Verify that the .prp file path is correct and that the Java process is running with the proper arguments.

If there is a data retrieval issue, double-check your connection string, ensure OAuth authentication (if used) is completed in the browser, and confirm that the JDBC driver is licensed and accessible from the driver path you provided.

Available tools

source_get_tables

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

source_get_columns

Retrieves a list of columns for a given table. The output is CSV with column headers in the first line.

source_run_query

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