Get the FREE Ultimate OpenClaw Setup Guide →

sugar-crm -by-cdata

This read-only MCP Server allows you to connect to Sugar CRM 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
Run this command in your terminal to add the MCP server to Claude Code.
Run in terminal:
Command
claude mcp add --transport stdio cdatasoftware-sugar-crm-mcp-server-by-cdata java -jar PATH/TO/CDataMCP-jar-with-dependencies.jar PATH/TO/sugar-crm.prp \
  --env JAVA_HOME="Path to JDK installation (if required)"

How to use

This MCP server exposes Sugar CRM data through a read-only MCP interface by wrapping the CData JDBC Driver for Sugar CRM. It enables local clients and AI tools to query live Sugar CRM data via standard MCP tools such as get_tables, get_columns, and run_query, without needing to write SQL on every request. The server runs a Java-based MCP process that reads a .prp configuration file to connect to Sugar CRM through the JDBC driver, and presents the results in a consistent JSON/CSV-delimited format for downstream clients.

To use it with Claude Desktop or similar clients, you configure an MCP server entry that points to the Java jar and the sugar-crm.prp file. Once configured, you can query available tables, inspect columns, and run SQL SELECT statements against Sugar CRM data as needed. The tools are named using the server prefix, for example: sugarcrm_by_cdata_get_tables, sugarcrm_by_cdata_get_columns, and sugarcrm_by_cdata_run_query. The JSON-RPC examples in the README illustrate how to invoke these tools programmatically if you’re scripting requests.

How to install

Prerequisites

  • Java Runtime Environment (JRE) or JDK installed
  • Maven installed (for building the MCP server)
  • Access to the CData JDBC Driver for Sugar CRM (download and install per license)
  • An environment where you can place the sugar-crm.prp file and the CData MCP jar

Installation steps

  1. Clone the repository and build the MCP server
git clone https://github.com/cdatasoftware/sugar-crm-mcp-server-by-cdata.git
cd sugar-crm-mcp-server-by-cdata
mvn clean install

This should produce the JAR named something like CDataMCP-jar-with-dependencies.jar in the target directory.

  1. Install the CData JDBC Driver for Sugar CRM
cd /path/to/CData JDBC Driver for Sugar CRM/lib
java -jar cdata.jdbc.sugarcrm.jar --license
  • If OAuth is used, you may need to complete authentication in your browser as directed by the driver utilities.
  1. Create a .prp configuration file for the JDBC connection
  • Create sugar-crm.prp with contents similar to the example below, filling in your values:
Prefix=sugarcrm
ServerName=CDataSugarCRM
ServerVersion=1.0
DriverPath=/path/to/cdata.jdbc.sugarcrm.jar
DriverClass=cdata.jdbc.sugarcrm.SugarCRMDriver
JdbcUrl=jdbc:sugarcrm:InitiateOAuth=GETANDREFRESH;
Tables=
  1. Run the MCP server
java -jar /path/to/CDataMCP-jar-with-dependencies.jar /path/to/sugar-crm.prp

Note: The MCP server uses stdio, so it is intended for clients running on the same machine.

  1. Configure Claude Desktop or other MCP clients
  • Add an MCP server entry pointing to the jar and the sugar-crm.prp, e.g. for Windows, the command path would point to java.exe and arguments would include -jar, the MCP jar, and the sugar-crm.prp path.
  • Ensure you fully quit and restart Claude Desktop after adding the new server entry so it appears in the UI.

Additional notes

Tips and common issues:

  • The server is read-only by design; write/update/delete capabilities are not exposed in this MCP server variant.
  • Ensure the JDBC driver is licensed and the connection string (JdbcUrl) is valid; use the DriverPath and DriverClass in the .prp file.
  • The Sugar CRM API surface will be exposed as tables and columns via the MCP interface; use the provided get_tables and get_columns tools to discover the schema before running queries.
  • If Claude Desktop doesn’t show the MCP server, fully quit Claude Desktop and re-open it to refresh the server list.
  • When moving between environments (Windows/Linux/macOS), paths in sugar-crm.prp and the CLI commands must be adjusted accordingly.
  • The server outputs results via standard output; consider using tools that parse the CSV output for easier consumption in downstream pipelines.

Related MCP Servers

Sponsor this space

Reach thousands of developers