Power BI Modeling
The Power BI Modeling MCP Server, brings Power BI semantic modeling capabilities to your AI agents.
What is Power BI Modeling?
Power BI Modeling is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to power bi modeling mcp server, brings power bi semantic modeling capabilities to your ai agents.
The Power BI Modeling MCP Server, brings Power BI semantic modeling capabilities to your AI agents.
This server falls under the Analytics category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- The Power BI Modeling MCP Server, brings Power BI semantic m
Use Cases
Maintainer
Works with
Installation
NPM
npx -y @microsoft/powerbi-modeling-mcpManual Installation
npx -y @microsoft/powerbi-modeling-mcpConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Power BI Modeling
Power BI Modeling MCP Server is a Microsoft-published MCP server that bridges AI agents and Power BI semantic models, enabling natural language control over modeling operations in Power BI Desktop, Fabric workspaces, and Power BI Project (PBIP/TMDL) files. It exposes over 20 tool groups covering tables, columns, measures, relationships, DAX queries, security roles, calculation groups, perspectives, translations, and more — making bulk operations like renaming hundreds of measures or generating multi-language translations a single AI-driven task. Data engineers and Power BI developers use it to automate repetitive modeling work, enforce naming conventions, document models, and execute and validate DAX queries without leaving their AI chat. The server is available as an npm package and as a Visual Studio Code extension.
Prerequisites
- Node.js installed (for npx-based installation)
- Power BI Desktop, a Fabric workspace, or Power BI Project (PBIP) files to connect to
- An MCP-compatible client: Visual Studio Code with GitHub Copilot Chat (recommended), or Claude Desktop
- GitHub Copilot subscription if using Visual Studio Code integration
- For Fabric workspace access: appropriate permissions on the Power BI workspace
Install via Visual Studio Code extension (recommended)
Install Visual Studio Code, the GitHub Copilot Chat extension, and then the Power BI Modeling MCP extension from the VS Code marketplace. The extension automatically registers the MCP server with Copilot.
Or add manually via npx for any MCP client
For Claude Desktop or other MCP clients, add the server to your configuration file using npx with the @microsoft/powerbi-modeling-mcp package and the --start argument.
Restart your MCP client
Quit and relaunch your MCP client (Claude Desktop or VS Code) so it picks up and starts the Power BI Modeling MCP server.
Connect to a Power BI semantic model
The first step in any session is to connect to a model. Use one of the three connection prompts depending on whether your model is in Power BI Desktop, a Fabric workspace, or a PBIP file on disk.
# For Power BI Desktop:
Connect to 'YourFileName' in Power BI Desktop
# For Fabric Workspace:
Connect to semantic model 'ModelName' in Fabric Workspace 'WorkspaceName'
# For PBIP files:
Open semantic model from PBIP folder '/path/to/definition/'Approve the confirmation prompt before making changes
The server uses the MCP Elicitation protocol and will ask for user confirmation before the first modification or query execution on a semantic model. Review the prompt and approve to proceed. You can skip this with --skipconfirmation in the args if preferred.
Power BI Modeling Examples
Client configuration
Add this to your claude_desktop_config.json or other MCP client config to use the npm package:
{
"mcpServers": {
"powerbi-modeling-mcp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@microsoft/powerbi-modeling-mcp@latest",
"--start"
]
}
}
}Prompts to try
Once connected to a semantic model, try these Power BI modeling tasks with your AI assistant:
- "Analyze my model's naming conventions and suggest renames to ensure consistency"
- "Add descriptions to all measures to explain their business logic and DAX code"
- "Generate a French translation for all tables, columns, and measures"
- "Refactor measures 'Sales Amount 12M Avg' and 'Sales Amount 6M Avg' into a calculation group"
- "Execute a DAX query to test my [Total Sales] measure"
- "Generate Markdown documentation for this semantic model including table relationships"Troubleshooting Power BI Modeling
powerbi-modeling-mcp does not appear in the VS Code Copilot tool list
Verify that the 'MCP servers in Copilot' option is enabled in your Copilot settings on GitHub.com. For enterprise accounts this setting is disabled by default and must be enabled by an administrator. After enabling, reload VS Code.
Cannot connect to Power BI Desktop — model not found
Ensure Power BI Desktop is open and the specific file is loaded before attempting to connect. Use the exact file name (without extension) in the connect prompt. If multiple Desktop instances are open, the server may need you to be more specific about which file to connect to.
Frequently Asked Questions about Power BI Modeling
What is Power BI Modeling?
Power BI Modeling is a Model Context Protocol (MCP) server that power bi modeling mcp server, brings power bi semantic modeling capabilities to your ai agents. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Power BI Modeling?
Install via npm with the command: npx -y @microsoft/powerbi-modeling-mcp. Then add the server configuration to your AI client's JSON config file (e.g., claude_desktop_config.json or .cursor/mcp.json).
Which AI clients work with Power BI Modeling?
Power BI Modeling works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Power BI Modeling free to use?
Yes, Power BI Modeling is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
Power BI Modeling Alternatives — Similar Analytics Servers
Looking for alternatives to Power BI Modeling? Here are other popular analytics servers you can use with Claude, Cursor, and VS Code.
OpenMetadata
★ 14.0kOpenMetadata is a unified metadata platform for data discovery, data observability, and data governance powered by a central metadata repository, in-depth column level lineage, and seamless team collaboration.
Superset
★ 10.9kAn MCP server that provides AI assistants with full access to Apache Superset instances, enabling interaction with dashboards, charts, datasets, databases, and SQL execution capabilities.
Horizon
★ 4.4k📡 Your own AI-powered news radar. Generates daily briefings in English & Chinese. | 用 AI 构建你专属的新闻雷达
MCP Server Chart
★ 4.1kEnables generation of 25+ types of charts and data visualizations using AntV, including bar charts, line charts, maps, mind maps, and specialized diagrams like fishbone and sankey charts. Supports both statistical charts and geographic visualizations
Muapi CLI
★ 997Official CLI for muapi.ai — generate images, videos & audio from the terminal. MCP server, 14 AI models, npm + pip installable.
Weather MCP Server
★ 907Weather Data Fetcher MCP server built with Node.js, MCP SDK, and Zod. Provides weather details like temperature and forecast for cities such as Noida and Delhi via a registered tool. Simplifies API integration, enabling structured responses for clien
Browse More Analytics MCP Servers
Explore all analytics servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Power BI Modeling in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Power BI Modeling?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.