microsoft/powerbi-modeling-mcp

The Power BI Modeling MCP Server, brings Power BI semantic modeling capabilities to your AI agents.

What it solves

This project provides a bridge between AI agents and Power BI semantic models. It allows users to manage and modify complex data models using natural language instead of manual configuration, enabling bulk operations, automated documentation, and agentic development workflows.

How it works

It implements the Model Context Protocol (MCP), acting as a local server that exposes Power BI modeling tools to AI agents. The server can connect to Power BI Desktop, Fabric workspaces, or Power BI Project (PBIP) files. Once connected, an AI agent can use the server's tools to execute modeling changes, run DAX queries, and manage model objects like tables, columns, and measures.

Who it’s for

Data engineers, Power BI developers, and AI application developers who want to automate the lifecycle of semantic modeling and integrate Power BI management into AI-driven workflows.

Highlights

  • Natural Language Modeling: Create and update tables, columns, and measures using plain text prompts.
  • Bulk Operations: Execute batch refactoring, renaming, or translations across hundreds of objects simultaneously.
  • DAX Integration: Execute and validate DAX queries to test measures and troubleshoot calculations.
  • Agentic Workflows: Supports TMDL and Power BI Project files for autonomous planning and execution of modeling tasks.
  • Comprehensive Toolset: Includes specialized operations for security roles, calculation groups, perspectives, and multi-language support.

Related

  • Project
    dbt-labs/dbt-mcp

    An MCP server that provides AI agents with tools to interact with dbt Core, Fusion, and Platform, enabling them to query data, manage lineage, and execute dbt workflows.

  • Project
    IBM/mcp

    A collection of Model Context Protocol (MCP) servers and tools that enable AI agents to securely interact with IBM products and enterprise resources.

  • Project
    googleapis/mcp-toolbox

    An open-source MCP server that connects AI agents and IDEs to enterprise databases via prebuilt generic tools or a custom framework for secure, structured data access.

  • Project
    sbroenne/mcp-server-excel

    An MCP server that enables AI agents to control the actual Microsoft Excel application on Windows via its COM API for end-to-end spreadsheet automation.

  • Project
    resend/resend-mcp

    An MCP server that connects AI agents to the Resend platform, enabling them to send and receive emails and manage email infrastructure via natural language.