This read-only MCP Server allows you to connect to Okta data from Claude Desktop through CData JDBC Drivers. For full CRUD support, check out our MCP Server for Okta (https://www.cdata.com/drivers/okta/download/mcp).
Configuration
View docs{
"mcpServers": {
"cdatasoftware-okta-mcp-server-by-cdata": {
"command": "java",
"args": [
"-jar",
"CDataMCP-jar-with-dependencies.jar",
"/PATH/TO/okta.prp"
]
}
}
}You can query live Okta data through a read-only MCP server powered by CData’s JDBC driver. This setup lets you ask natural-language questions and retrieve up-to-date information without writing SQL.
After you configure the MCP server, you can use any MCP client to ask questions about your Okta data. The server exposes data through standard MCP tools, so you can retrieve tables, inspect columns, and run read-only queries. Examples of typical questions include asking about user status across groups, active sessions, or user attributes over time. You do not need SQL knowledge; simply request the information you want and the client will translate it into the appropriate read operations against Okta.
Prerequisites you need before installing this MCP server are a Java runtime and Maven for building the project.
git clone https://github.com/cdatasoftware/okta-mcp-server-by-cdata.git
cd okta-mcp-server-by-cdata
```
```
mvn clean install
```
This builds the server and creates the JAR file: CDataMCP-jar-with-dependencies.jar. You will also need the CData JDBC Driver for Okta, which you download separately.Install the CData JDBC Driver for Okta from the official driver page. Then license the driver to enable usage.
java -jar cdata.jdbc.okta.jar --license
```
Enter your name, email, and your license key (or TRIAL if you are evaluating).Configure the connection to Okta using the driver’s connection string utility, and copy the resulting JDBC URL for use in the MCP configuration.
java -jar cdata.jdbc.okta.jar
```
Use the utility to build and test the connection string. If OAuth is used, authenticate in your browser. Copy the generated connection string for later use.Create a configuration file (example named okta.prp) with the JDBC connection details and table access settings. The sample shows the required fields and how to wire them together.
Prefix=okta
ServerName=CDataOkta
ServerVersion=1.0
DriverPath=PATH\TO\cdata.jdbc.okta.jar
DriverClass=cdata.jdbc.okta.OktaDriver
JdbcUrl=jdbc:okta:InitiateOAuth=GETANDREFRESH;
Tables=
```
Adjust the DriverPath and JdbcUrl to match your environment and the connection string produced earlier.The final step is to run the MCP server with the prepared configuration.
java -jar /PATH/TO/CDataMCP-jar-with-dependencies.jar /PATH/TO/okta.prp
```
Note: The server runs in stdio mode and can only be accessed by clients on the same machine.To enable usage with Claude Desktop or another MCP client, place the server command in the client’s MCP configuration, pointing to the okta.prp file you created. The client will then expose tools to list tables, list columns, and run read-only queries against Okta data.
This MCP server presents the following tools for read-only access to Okta data: - okta_get_tables: Retrieves a list of tables available in the data source. Output is CSV with headers. - okta_get_columns: Retrieves a list of columns for a specified table. Output is CSV with headers. - okta_run_query: Executes a SQL SELECT query against the data source.
If you cannot see the Okta MCP server in your MCP client, fully quit and relaunch the client. Ensure the okta.prp file paths are correct and that the JDBC driver is licensed. If you encounter connection issues, verify the connection string and re-test the connection using the driver utility. For further help, contact CData Support or join the CData Community.
This MCP server is distributed under the MIT License. You are free to use, modify, and distribute the software in compliance with the MIT terms. See the LICENSE file for full details.
Retrieves a list of tables available in the Okta data source. The output is in CSV format with column headers.
Retrieves a list of columns for a specified table. The output is in CSV format with column headers.
Executes a SQL SELECT query against the Okta data source and returns the results.