home / mcp / zoho creator mcp server

Zoho Creator MCP Server

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

You can query live Zoho Creator data through a local MCP server that exposes the data via a simple MCP interface. This lets you ask natural-language questions and get up-to-date results from Zoho Creator without writing SQL. The server runs locally, is read-only by default, and is designed to be used with MCP clients to retrieve and read data efficiently.

How to use

Once you have the MCP server running, you can use a compatible MCP client to ask questions about your Zoho Creator data. You don’t need to know SQL or manage complex connections; the client will send requests to the MCP server and return structured results. Typical usage includes asking for counts, summaries, or correlations across Zoho Creator tables, and validating live data directly from your data source.

How to install

Prerequisites you need before installation:

• Java Runtime Environment (JRE) installed on your machine.

How to install

git clone https://github.com/cdatasoftware/zoho-creator-mcp-server-by-cdata.git
cd zoho-creator-mcp-server-by-cdata
mvn clean install

How to install

Next, download and install the CData JDBC Driver for Zoho Creator from the driver page. Then license the driver, configure a JDBC connection, and create a .prp file for the MCP server as described in the following steps.

How to install

Install and license the driver, then configure a connection using the JDBC Connection String utility. Copy the resulting connection string for use in the .prp file.

How to install

Create the MCP configuration file (zoho-creator.prp) with the required properties and values. Example structure is shown below.

How to install

Prefix=zohocreator
ServerName=CDataZohoCreator
ServerVersion=1.0
DriverPath=PATH\\TO\\cdata.jdbc.zohocreator.jar
DriverClass=cdata.jdbc.zohocreator.ZohoCreatorDriver
JdbcUrl=jdbc:zohocreator:InitiateOAuth=GETANDREFRESH;
Tables=

How to install

Run the MCP server locally using Java and pass the .prp file you created. The command is shown in the example below.

How to install

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

How to use

You can start Claude Desktop or another MCP client and add the Zoho Creator MCP server configuration. The server runs on stdio, so the client and server must be on the same machine unless the MCP wrapper is configured otherwise.

Additional sections

Configuration details, troubleshooting tips, and licensing information are provided to help you set up and use the MCP server smoothly. The server is designed to expose Zoho Creator data as read-only, enabling safe querying from LLMs and other clients.

Troubleshooting

If the MCP server does not appear in your MCP client, ensure you have fully exited and restarted the client so it detects new servers. Verify your .prp file and connection string are correct. If you run into data retrieval issues, double-check the JDBC driver license status and the connection string configuration.

License

This MCP server is released under the MIT License. You may use, modify, and distribute the software in accordance with the terms of that license.

All supported sources

Zoho Creator is exposed via a JDBC driver so the MCP server can present it as relational-like data sources for read operations.

Available tools

source_get_tables

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

source_get_columns

Retrieves a list of columns for a given table. Output is in CSV with headers as the first line.

source_run_query

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