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, allowing users to manage and modify their data models using natural language instead of manual configuration. It eliminates repetitive manual tasks like bulk renaming, refactoring DAX measures, and documenting models, which can otherwise take hours of work.

How it works

It implements the Model Context Protocol (MCP) to act as a local server that connects AI agents (such as those in VS Code with GitHub Copilot) to Power BI Desktop, Fabric workspaces, or Power BI Project (PBIP) files. The server exposes a wide array of tools that the AI agent can call to execute modeling operations—such as creating tables, managing relationships, and validating DAX queries—directly on the semantic model.

Who it’s for

Data engineers, Power BI developers, and analysts who want to automate the semantic modeling process and use AI to accelerate development, refactor code, and maintain documentation.

Highlights

  • Natural Language Modeling: Create, update, and manage tables, columns, and measures using plain English.
  • Bulk Operations: Execute batch changes across hundreds of objects simultaneously with transaction support.
  • Agentic Workflows: Supports TMDL and PBIP files, enabling AI agents to autonomously plan and execute complex tasks.
  • DAX Integration: Execute and validate DAX queries to troubleshoot calculations and explore data.
  • Comprehensive Toolset: Includes specialized tools for security roles, calculation groups, partitions, and multi-language translations.

Related

  • Project
    dbt-labs/dbt-mcp

    dbt‑MCP Server is an open‑source service that exposes a large catalog of dbt‑related tools (SQL execution, semantic‑layer queries, model discovery, dbt CLI commands, job administration, code generation, and documentation lookup) via the Model Context Protocol. It lets LLM‑powered agents understand and act on a dbt project—generating SQL from natural language, running dbt jobs, fetching lineage, and even creating new model files—making it a concrete bridge between data‑engineering metadata and AI assistants.

  • Project
    googleapis/mcp-toolbox

    MCP Toolbox is an open‑source server that lets AI agents and IDEs talk to enterprise databases via the Model Context Protocol. It offers ready‑made database tools and a framework for defining custom, secure SQL/semantic‑search tools, with SDKs for Python, JS/TS, Go, and Java.

  • Project
    salesforcecli/mcp

    An MCP server that enables LLMs and AI agents to securely read, manage, and operate Salesforce orgs through a standardized set of tools.

  • 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 full automation of data analytics and workbook management.

  • Project
    ivnvxd/mcp-server-odoo

    An MCP server that enables AI assistants to interact with Odoo ERP systems, allowing users to search, create, and manage business data via natural language.