home / mcp / adobe analytics mcp server

Adobe Analytics MCP Server

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

You deploy a local, read-only MCP server that exposes live Adobe Analytics data through a simple MCP interface. This lets you ask natural language questions and receive live results without writing SQL.

How to use

Set up your MCP server, then connect your preferred client. You will interact with the server using the built-in tools to explore the data catalog, inspect table schemas, and run read-only queries. You can ask questions like which accounts have the most active campaigns this month, or retrieve counts of records in a given table. The server focuses on safe, read-only access to Adobe Analytics data exposed via the CData JDBC Driver.

Key concepts you will use in practice:

Get the list of available tables with adobe_analytics_get_tables
Get columns for a specific table with adobe_analytics_get_columns
Run a read-only query with adobe_analytics_run_query

How to install

{
  "mcpServers": {
    "adobe_analytics_mcp": {
      "type": "stdio",
      "name": "adobe_analytics_mcp",
      "command": "java",
      "args": [
        "-jar",
        "PATH/TO/CDataMCP-jar-with-dependencies.jar",
        "PATH/TO/adobe-analytics.prp"
      ],
      "env": []
    }
  }
}

Additional configuration steps

Build prerequisites include a Java runtime and a MCP server JAR. You also need the CData JDBC Driver for Adobe Analytics licensed and configured. Follow the steps to license the driver, configure the JDBC connection, and create the .prp file that points to your Adobe Analytics data source.

Troubleshooting

If the MCP server does not appear in your client, ensure you have fully restarted the client after starting the server. Verify that the Java process is running and that the path to the JAR and the .prp file is correct. If you encounter connection issues, double-check the JDBC Driver license status and the PRP connection string.

Notes

This server is read-only by design, providing safe access for natural language queries against live Adobe Analytics data. If you need write, update, or delete capabilities, consider the full MCP Server option that supports read/write access.

Available tools

adobe_analytics_get_tables

Retrieves a list of tables available in the data source. Output is CSV with headers in the first line.

adobe_analytics_get_columns

Retrieves a list of columns for a specified table. Output is CSV with headers in the first line.

adobe_analytics_run_query

Executes a SQL SELECT query against the exposed data source and returns results.