SAP HANA

Provides a read-only MCP server to query live SAP HANA data via the CData JDBC Driver.

other

3

GitHub Stars

other

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "cdatasoftware-sap-hana-mcp-server-by-cdata": {
      "command": "java",
      "args": [
        "-jar",
        "/PATH/TO/CDataMCP-jar-with-dependencies.jar",
        "/PATH/TO/Salesforce.prp"
      ],
      "env": {
        "JAVA_TOOL_OPTIONS": "-Xmx2g"
      }
    }
  }
}

You can run a local, read-only MCP server that exposes live SAP HANA data through a simple MCP interface. This lets you ask natural language questions and receive up-to-date results from SAP HANA without writing SQL.

How to use

You will run a local MCP server that exposes SAP HANA data to your MCP client. Start the server on your machine and point your client to the built-in tools to discover tables, fetch columns, and run read-only queries. Ask questions like “What is the status of opportunities by industry?” or “Show me open tickets for the SUPPORT project.” The MCP client will automatically use the available tools to read data from SAP HANA through the MCP interface.

How to install

# Prerequisites
- Java 8+ installed on your machine
- Maven for building the MCP server

# 1. Clone the project and enter the directory
git clone https://github.com/cdatasoftware/sap-hana-mcp-server-by-cdata.git
cd sap-hana-mcp-server-by-cdata

# 2. Build the server to generate the JAR with dependencies
mvn clean install

# 3. Prepare the SAP HANA JDBC driver and license steps are performed externally
# - Install the CData JDBC Driver for SAP HANA (driver package from CData)
# - License the driver using the provided JAR in the lib folder

# 4. Create a .prp file that configures the JDBC connection (sap-hana.prp)
#   Use the example properties as a template and fill in your values

Additional configuration and usage notes

The server runs as a local stdio process, which means it communicates with clients running on the same machine. You’ll invoke it via a Java command that starts the MCP server using your prepared .prp file. The following illustrates the runtime pattern you will use after you have your sap-hana.prp ready.

java -jar /PATH/TO/CDataMCP-jar-with-dependencies.jar /PATH/TO/sap-hana.prp

Tools and how they are exposed

When connected, the MCP server provides tools to discover and query the SAP HANA data source. The tools are named with the server prefix and used to fetch metadata or execute queries.

Troubleshooting

If the MCP server does not appear in your MCP client, ensure you have fully exited and restarted the client after starting the server. Verify your sap-hana.prp is correctly formed and that the JDBC driver is licensed and accessible. If connection issues persist, re-create the connection string using the JDBC driver’s connection utility and update the .prp file accordingly.

Notes on licensing and sources

This MCP server is provided as a read‑only interface to live SAP HANA data via the CData JDBC Driver. Ensure you comply with the driver’s licensing terms and that you use a valid license when running the MCP stack in your environment.

Available tools

sap_hana_get_tables

Retrieves a list of tables available in the SAP HANA data source. Output is in CSV format with a header row.

sap_hana_get_columns

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

sap_hana_run_query

Executes a SQL SELECT query against the SAP HANA data source.