Ssas MCP Server

MCP server for querying SQL Server Analysis Services (SSAS) via DAX and MDX

Local serverstdioPython

What is the Ssas MCP server?

Connect Ssas to Claude, Cursor or any other MCP client and it stops being a tab you switch to. MCP server for querying SQL Server Analysis Services (SSAS) via DAX and MDX. The ssas mcp server is what makes that connection.

What the server does

A Model Context Protocol (MCP) server that connects AI agents to SQL Server Analysis Services (SSAS). It lets tools like GitHub Copilot, Claude (via Codex or Claude Code), and other MCP clients run DAX and MDX queries, explore models, and list measures, all through natural language.

Installation

ssas-mcp-server on PyPI is all you need. Most clients run it directly, so configuration is a few lines and a restart.

Credentials and setup notes

Configuration is passed through the environment: SSAS_SERVER, SSAS_DATABASE, ADOMD_DLL_PATH. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.

  1. Python 3.10+ 2. ADOMD.NET client library \ The DLL Microsoft.AnalysisServices.AdomdClient.dll must be present on the machine. It ships with any of these: - SQL Server Management Studio (SSMS) - Power BI Desktop - The standalone AMO/ADOMD client libraries The server auto-detects common install locations. If your

Worth knowing first

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Where it fits

Among the database access options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes.

SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.

How to install the Ssas MCP server

{
  "mcpServers": {
    "ssas": {
      "command": "ssas-mcp-server",
      "env": {
        "SSAS_SERVER": "SERVER\\INSTANCE",
        "SSAS_DATABASE": "My Cube"
      }
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Configuration

  1. Python 3.10+ 2. ADOMD.NET client library \ The DLL Microsoft.AnalysisServices.AdomdClient.dll must be present on the machine. It ships with any of these: - SQL Server Management Studio (SSMS) - Power BI Desktop - The standalone AMO/ADOMD client libraries The server auto-detects common install locations. If your
VariableDescriptionRequired
SSAS_SERVERConfiguration value read at startup.Optional
SSAS_DATABASEConfiguration value read at startup.Optional
ADOMD_DLL_PATHFilesystem location the server is allowed to use.Optional

Frequently asked questions

It connects Ssas to MCP-compatible AI assistants such as Claude and Cursor. Instead of copying data back and forth by hand, the assistant works with Ssas directly.