Get the FREE Ultimate OpenClaw Setup Guide →

sas-data-sets -by-cdata

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

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-sas-data-sets-mcp-server-by-cdata java -jar CDataMCP-jar-with-dependencies.jar /PATH/TO/sas-data-sets.prp \
  --env JAVA_TOOL_OPTIONS="Optional: set if needed" \
  --env CDATA_JDBC_LICENSE_PATH="Path to license if required by driver"

How to use

This MCP server provides a read-only interface to SAS Data Sets via the CData JDBC Driver. It wraps the driver in a simple MCP layer so large language models and clients can question live SAS Data Sets without writing SQL. Once running, Claude Desktop or other MCP clients can discover the server and invoke the built-in tools to list tables, view columns, or run read-only queries. The server exposes three tools: sas_data_sets_get_tables, sas_data_sets_get_columns, and sas_data_sets_run_query. Use the get_tables tool to learn what tables exist, then call get_columns for a specific table to inspect its schema, and finally use run_query to execute a SELECT-like query against the SAS Data Sets. Interactions are performed via JSON-RPC, following the standard MCP tool-calling patterns described in the README.

How to install

Prerequisites:

  • Java (JDK 8+)
  • Maven (for building the MCP server JAR)
  • SAS Data Sets access via the CData JDBC Driver
  • CData JDBC Driver for SAS Data Sets (with license)

Installation steps:

  1. Clone the repository git clone https://github.com/cdatasoftware/sas-data-sets-mcp-server-by-cdata.git cd sas-data-sets-mcp-server-by-cdata

  2. Build the MCP server JAR mvn clean install This produces CDataMCP-jar-with-dependencies.jar (in the target or build output).

  3. Install the CData JDBC Driver for SAS Data Sets

  4. Prepare the JDBC connection properties (.prp) for Claude Desktop or the MCP runner

    • Create sas-data-sets.prp with the required properties (Prefix, ServerName, ServerVersion, DriverPath, DriverClass, JdbcUrl, Tables).
    • Example content is provided in the README under the Setup Guide.
  5. Run the MCP server

    • Ensure the .prp file path is accessible and then start the server: java -jar CDataMCP-jar-with-dependencies.jar /PATH/TO/sas-data-sets.prp
    • The server uses stdio, so you’ll typically run it on the same machine as the client.
  6. Connect with Claude Desktop or your MCP client by configuring mcpServers to point to this server, using the command and arguments shown in the mcp_config section.

Additional notes

Tips and common issues:

  • The MCP server is read-only by design in this package. For full CRUD capabilities, consider the full CData MCP Server for SAS Data Sets.
  • If Claude Desktop doesn’t show the MCP server, fully quit and re-launch the client, then refresh. Ensure the .prp file path is correct and the JDBC Driver is licensed.
  • The JDBC connection string in the .prp file must be valid and tested via the driver’s Connection String utility before using it with the MCP server.
  • Since the server runs over stdio, it must be hosted on the same machine as the client tooling that invokes it.
  • If you need to adjust server parameters, modify sas-data-sets.prp accordingly and restart the MCP server.
  • Environment variables are optional, but you can set JAVA_TOOL_OPTIONS or provide a LICENSE path for the driver if your environment requires it.

Related MCP Servers

Sponsor this space

Reach thousands of developers