home / mcp / azure analysis services mcp server

Azure Analysis Services MCP Server

Queries live Azure Analysis Services data via MCP using the CData JDBC driver in a read-only MCP server.

Installation

Add the following to your MCP client configuration file.

Configuration

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

You have a local, read-only MCP server that makes Azure Analysis Services data accessible to AI assistants via the CData JDBC Driver. This server wraps the driver and exposes live data through a simple MCP interface, letting you ask natural language questions and get up-to-date results without writing SQL.

How to use

Operate the MCP server from your local machine and connect your AI client to it. The server runs as a local process and communicates with clients via standard input/output (stdio). You can ask questions like which opportunities are latest in your pipeline or how many tickets are open, and the AI client will query Azure Analysis Services through the MCP layer.

Typical usage patterns include starting the server on demand, testing the connection, and then querying through your AI client. You do not need to write SQL; simply pose questions in natural language and rely on the MCP server to translate them into data requests.

How to install

Prerequisites you need before installing: - Java Runtime Environment (JRE) or JDK 8 or newer - Maven for building the MCP server (optional if you use a prebuilt artifact) - Access to the CData JDBC Driver for Azure Analysis Services and a valid license (trial is supported)

Clone the project and build the MCP server locally. Run these commands in your terminal or command prompt:

git clone https://github.com/cdatasoftware/azure-analysis-services-mcp-server-by-cdata.git
cd azure-analysis-services-mcp-server-by-cdata
mvn clean install

Obtain and install the CData JDBC Driver for Azure Analysis Services. Follow the provided steps to license and configure the driver, then generate a JDBC connection string using the driver’s Connection String utility. Save the resulting string for later use.

Create a properties file that defines how the MCP server should connect to your data source. Use the following example as a template and fill in your actual paths and connection details:

Prefix=aas
ServerName=CDataAAS
ServerVersion=1.0
DriverPath=PATH\TO\cdata.jdbc.aas.jar
DriverClass=cdata.jdbc.aas.AASDriver
JdbcUrl=jdbc:aas:InitiateOAuth=GETANDREFRESH;
Tables=

Additional configuration and running the server

Prepare a JSON or properties-based configuration that points the MCP server to the JDBC connection. You will run the MCP server with this configuration so it can expose the data to clients.

Run the MCP server locally using the provided JAR and your configuration file. The final run command is shown here:

java -jar /PATH/TO/CDataMCP-jar-with-dependencies.jar /PATH/TO/azure-analysis-services.prp

Notes on using with Claude Desktop

If you are using Claude Desktop or another MCP-enabled client, configure the client to load your MCP server by adding an entry that points to the local command and the MCP configuration file. The server runs on your machine and the client connects to it locally.

Tip: fully quit and restart your client after adding or updating the MCP server configuration so the server appears in the client’s list.

Tools & Descriptions

The MCP server exposes a small set of tools to discover data and run queries. Use these to explore tables, columns, and to execute reads.

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

Available tools

aas_get_tables

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

aas_get_columns

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

aas_run_query

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