home / mcp / ssas mcp server

SSAS MCP Server

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

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

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

This MCP server wraps the CData JDBC Driver for SQL Server Analysis Services to expose live SSAS data through a simple MCP interface. You can ask natural language questions and retrieve up-to-date SSAS information without writing SQL, enabling LLMs to read data directly from SQL Server Analysis Services.

How to use

You connect your MCP client to this server and use built-in tools to explore and query SSAS data. You can ask questions like the correlations between opportunities and accounts, counts of current items in a project, or calendar events for today. The server handles the data access and returns results in a format suitable for your AI client, so you don’t need to write SQL queries yourself.

How to install

Prerequisites: you need Java installed to run the MCP server runtime.

# 1) Clone the repository
git clone https://github.com/cdatasoftware/ssas-mcp-server-by-cdata.git
cd ssas-mcp-server-by-cdata

# 2) Build the server
mvn clean install
# This creates the JAR: CDataMCP-jar-with-dependencies.jar

Next, install and license the CData JDBC Driver for SQL Server Analysis Services, then configure your connection and create a .prp file following the provided properties.

# 3) Download the driver from the vendor and install it
# (Follow the vendor's installer steps for your OS)

# 4) License the driver
# Windows: java -jar cdata.jdbc.ssas.jar --license
# Mac/Linux: java -jar cdata.jdbc.ssas.jar --license

# 5) Configure your connection using the Connection String utility
java -jar cdata.jdbc.ssas.jar
# Test the connection and copy the connection string for later use

Create a properties file for your JDBC connection (example name: ssas.prp) with the required fields and your JDBC URL, then save it.

Prefix=ssas
ServerName=CDataSSAS
ServerVersion=1.0
DriverPath=PATH\TO\cdata.jdbc.ssas.jar
DriverClass=cdata.jdbc.ssas.SSASDriver
JdbcUrl=jdbc:ssas:InitiateOAuth=GETANDREFRESH;
Tables=

Additional setup notes

To run the MCP server on its own, use the final runtime command that points to your .prp file.

java -jar /PATH/TO/CDataMCP-jar-with-dependencies.jar /PATH/TO/Salesforce.prp

Configuration and usage notes

The server runs locally and exposes actions through MCP for LLMs. You typically interact with it via an MCP client that can load the server configuration and call the available tools. If you need to join multiple data sources or want to manage access, ensure your JDBC driver is licensed and your connection string is tested successfully.

Troubleshooting

If you cannot see or connect to the MCP server, fully quit the client and restart it so the server appears. If the client cannot retrieve data, double-check your connection string and test the connection again. If you still have issues, contact CData Support or join the CData Community for help.

Tools & descriptions

The MCP server provides the following tools to discover and query data. Replace {servername} with the server name you configured.

Tools

{servername}_get_tables - Retrieves a list of tables available in the data source. Use {servername}_get_columns to list available columns for a table. Output is CSV with headers.
{servername}_get_columns - Retrieves a list of columns for a table. Use {servername}_get_tables to get tables. Output is CSV with headers.
{servername}_run_query - Execute a SQL SELECT query

Available tools

ssas_get_tables

Retrieves a list of tables available in the data source. The output is in CSV format with the first line containing column headers.

ssas_get_columns

Retrieves a list of columns for a specified table. The output is in CSV format with the first line containing column headers.

ssas_run_query

Executes a SQL SELECT query against the connected data source.