home / mcp / salesforce data cloud mcp server

Salesforce Data Cloud MCP Server

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

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

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

You will run a read-only MCP server that exposes live Salesforce Data Cloud data through a simple MCP interface. This lets you ask natural language questions and get up-to-date results without writing SQL, while the underlying CData JDBC Driver handles the connection to Salesforce Data Cloud.

How to use

After you configure the MCP server, you can interact with it using an MCP client. You do not need to write SQL queries; instead, you ask questions in natural language and the client translates them into data retrieval actions. You can discover available data and then ask targeted questions such as retrieving the list of tables, inspecting column metadata, or querying specific data slices like opportunities or calendar events. Use the built-in tools to explore the data model and run read-only queries against Salesforce Data Cloud.

How to install

Prerequisites before you begin - Install Java Runtime Environment (JRE) compatible with the MCP server - Install Maven for building the MCP project - Have internet access to download the CData JDBC Driver for Salesforce Data Cloud when you configure the data source

Step 1: Clone the project and build the MCP server

git clone https://github.com/cdatasoftware/salesforce-data-cloud-mcp-server-by-cdata.git
cd salesforce-data-cloud-mcp-server-by-cdata
mvn clean install

Step 2: Prepare the CData JDBC Driver for Salesforce Data Cloud

Download and install the CData JDBC Driver for Salesforce Data Cloud from the CData site.

https://www.cdata.com/drivers/salesforcedc/download/jdbc

Step 3: License the CData JDBC Driver

Locate the lib folder in your installation and license the driver.

java -jar cdata.jdbc.salesforcedatacloud.jar --license

Step 4: Configure the connection to Salesforce Data Cloud

Run the Connection String utility to create and test your JDBC URL.

java -jar cdata.jdbc.salesforcedatacloud.jar

Step 5: Create the JDBC profile file

Create a .prp file with your connection details. This file feeds the MCP server with the necessary properties.

env
Prefix=salesforcedatacloud
ServerName=CDataSalesforceDataCloud
ServerVersion=1.0
DriverPath=PATH\\TO\\cdata.jdbc.salesforcedatacloud.jar
DriverClass=cdata.jdbc.salesforcedatacloud.SalesforceDataCloudDriver
JdbcUrl=jdbc:salesforcedatacloud:InitiateOAuth=GETANDREFRESH;
Tables=

Step 6: Configure Claude Desktop or your MCP client

Create a client configuration that points to the MCP server. The client will load your MCP profile and start querying data.

Step 7: Run the MCP server

Start the MCP server using the final runtime command shown in the setup. The server runs on stdio and communicates with a local client.

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

Available tools

salesforce_get_tables

Retrieves a list of tables available in the data source. The output is provided in CSV format with a header row.

salesforce_get_columns

Retrieves a list of columns for a specified table. The output is provided in CSV format with a header row.

salesforce_run_query

Executes a SQL SELECT query against the connected data source to retrieve results.