home / mcp / sap ariba source mcp server

SAP Ariba Source MCP Server

This read-only MCP Server allows you to connect to SAP Ariba Source 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

Add the following to your MCP client configuration file.

Configuration

View docs

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

You can run a local, read-only MCP server that exposes SAP Ariba Source data through the CData JDBC Driver. This server makes live SAP Ariba Source data searchable by natural language queries via an MCP client, with no SQL required. It’s ideal for asking questions like what opportunities are open or how many tickets are in a project today.

How to use

Once the MCP server is running, connect your MCP client (for example Claude Desktop) to the SAP Ariba Source MCP server. You will access live SAP Ariba Source data through built-in tools that let you read information and run queries. You can ask natural language questions like “What is the correlation between my closed won opportunities and the account industry?” or “How many open tickets do I have in the SUPPORT project?” The server exposes tools to list tables, list columns, and execute read queries against the SAP Ariba Source data.

How to install

# Prerequisites
- Java and Maven installed on your machine
- A SAP Ariba Source data connection via the CData JDBC Driver

# 1) Build the MCP server
git clone https://github.com/cdatasoftware/sap-ariba-source-mcp-server-by-cdata.git
cd sap-ariba-source-mcp-server-by-cdata
mvn clean install
# This creates the JAR: CDataMCP-jar-with-dependencies.jar

# 2) Install the CData JDBC Driver for SAP Ariba Source
# Download from the CData site and install following their instructions

# 3) License the JDBC Driver
# Example path names will vary by OS
java -jar cdata.jdbc.saparibasource.jar --license
# Enter your name, email, and TRIAL (or your license key)

# 4) Configure your connection to the data source
java -jar cdata.jdbc.saparibasource.jar
# Use the Connection String utility, Test Connection, and copy the connection string

# 5) Create a .prp file for the JDBC connection
# Example sap-ariba-source.prp
Prefix=saparibasource
ServerName=CDataSAPAribaSource
ServerVersion=1.0
DriverPath=PATH\TO\cdata.jdbc.saparibasource.jar
DriverClass=cdata.jdbc.saparibasource.SAPAribaSourceDriver
JdbcUrl=jdbc:saparibasource:InitiateOAuth=GETANDREFRESH;
Tables=

# 6) Run the MCP server
java -jar /PATH/TO/CDataMCP-jar-with-dependencies.jar /PATH/TO/sap-ariba-source.prp
```

This setup runs the MCP server locally using standard IO (stdio) mode, so the server and client must run on the same machine. Replace the PATH placeholders with your actual paths and file names.

Additional configuration and notes

The MCP server is designed to be run locally and queried by an MCP client on the same host. You configure the SAP Ariba Source connection once via the JDBC Driver helper tool, then reference the resulting .prp file when starting the MCP server. No SQL knowledge is required to ask questions; the server translates natural language requests into the appropriate data queries behind the scenes.

Troubleshooting

If you cannot see your MCP Server in your client, ensure you have fully quit and restarted the client so it reloads the server list. If the client cannot retrieve data, verify the JDBC connection string was created correctly and that you copied the exact string into the sap-ariba-source.prp file. If you have trouble connecting to the data source, ensure the CData JDBC Driver is licensed and the connection string is valid. For broader assistance, contact CData Support or join the CData Community.

Tools and endpoints

The SAP Ariba Source MCP Server exposes the following tools in the MCP client: the server Name_get_tables to list available tables, the serverName_get_columns to list columns for a table, and serverName_run_query to execute a SQL SELECT against the data. Use the outputs to discover table structures and then query specific data as needed.

Available tools

saparibasource_get_tables

Retrieves a list of tables available in the SAP Ariba Source data source. The output will be in CSV with column headers in the first line.

saparibasource_get_columns

Retrieves a list of columns for a specific table. The output will be in CSV with column headers in the first line.

saparibasource_run_query

Executes a SQL SELECT query against the SAP Ariba Source data and returns the result set.