home / mcp / oracle eloqua mcp server

Oracle Eloqua MCP Server

This read-only MCP Server allows you to connect to Oracle Eloqua 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-oracle-eloqua-mcp-server-by-cdata": {
      "command": "java",
      "args": [
        "-jar",
        "CDataMCP-jar-with-dependencies.jar",
        "PATH/TO/oracle-eloqua.prp"
      ]
    }
  }
}

You can query live Oracle Eloqua data through a local MCP server that wraps the CData JDBC Driver, exposing data as simple MCP endpoints. This enables AI clients to ask natural language questions and retrieve up-to-date Eloqua information without writing SQL, while keeping data access read-only and secure on your machine.

How to use

After you have the MCP server running, connect your AI client to the local MCP endpoint. You will interact with the built-in tools to discover available tables, view columns, and run read-only queries that return results in a structured format (CSV-like output). Ask natural language questions like “What is the pipeline status for Q3 campaigns?” or “Show me the most recent Eloqua campaign results by segment.” The server translates your requests into SQL behind the scenes and returns the results to your client without you writing SQL.

How to install

Prerequisites: Ensure you have a Java runtime installed on your machine. You also need a Maven build environment to compile the MCP server from source.

1) Clone the project and enter its directory.

git clone https://github.com/cdatasoftware/oracle-eloqua-mcp-server-by-cdata.git
cd oracle-eloqua-mcp-server-by-cdata

2) Build the server to generate the executable JAR.

mvn clean install
```
This produces the JAR named `CDataMCP-jar-with-dependencies.jar` in your target directory.

3) Obtain and license the CData JDBC Driver for Oracle Eloqua from the official source and install it on your system following the driver’s setup workflow.

4) Create a JDBC connection profile for Eloqua and save the resulting connection string into a property file (for example oracle-eloqua.prp). The file must include settings for Prefix, ServerName, ServerVersion, DriverPath, DriverClass, JdbcUrl, and Tables.

5) Prepare a Claude Desktop config snippet (or equivalent) to register your MCP server by pointing to the JAR and the .prp file. The command uses the Java runtime to launch the MCP server with the connection profile.

Additional sections

Configuration notes: The MCP server is intended to run locally with read-only access to Eloqua data. You will typically provide a JDBC connection string that uses OAuth or other Eloqua authentication flows supported by the CData JDBC Driver, and you will reference the resulting .prp file when launching the MCP server.

Security and access: Since this server runs on your machine, ensure your machine’s firewall allows local connections only and that you restrict access to the client software that consumes MCP data. Do not expose the local MCP endpoint to untrusted networks.

Troubleshooting: If the MCP server does not appear in your client, fully exit the client and restart it. Verify that the MCP process is running and that the path to the .prp file is correct. If data cannot be retrieved, revalidate the connection string in the .prp file and test the connection via the driver’s connection utility. If issues persist, contact support for assistance.

Notes

The server operates in a stdio mode, meaning it is designed to run on the same machine as the client that starts it. Use the provided command to launch the server and pass the path to your Eloqua connection profile.

Available tools

eloqua_get_tables

Retrieves the list of available tables in the Eloqua data source. Returns a CSV with a header row and subsequent rows for each table.

eloqua_get_columns

Retrieves the list of columns for a specified table. Returns a CSV with a header row describing column names and types.

eloqua_run_query

Executes a SQL SELECT query against the Eloqua data source and returns the resulting dataset.