Power BI Tabular MCP server

Connects to locally running Power BI Desktop tabular models via ADOMD.NET, enabling DAX query execution, metadata exploration, and model analysis with automatic instance discovery and comprehensive error reporting for Power BI development and troubleshooting.
Back to servers
Setup instructions
Provider
jonaolden
Release date
Jul 26, 2025
Language
Python
Stats
10 stars

This MCP server enables communication with local Tabular Models in PowerBI Desktop through the Model Context Protocol (MCP). It allows LLM clients like Copilot to query your tabular models, helping you debug, analyze, and compose DAX queries with ease.

Installation

Using Pre-built Executables

For the fastest setup:

  1. Download the pre-built executable from the Releases section
  2. Configure your Power BI connection by running:
Releases\pbi-local-mcp.DiscoverCli.exe
  1. Follow the prompts to detect your Power BI instance and create the .env file

Configuring VS Code MCP Integration

Set up your VS Code integration by configuring the mcp.json file:

{
  "mcpServers": {
    "MCPBI": {
      "command": "C:\\dir\\to\\mcpbi.exe",
      "args": []
    }
  }
}

Using With Known PowerBI Port

If you already know which port your PowerBI Tabular model is running on (visible in Tabular Editor):

{
  "mcpServers": {
    "MCPBI": {
      "command": "C:\\dir\\to\\mcpbi.exe",
      "args": ["--port","12345"]
    }
  }
}

Available Tools

Working with Measures

ListMeasures

Lists all measures in the model with essential information (name, table, data type, visibility). You can optionally filter by table name.

GetMeasureDetails

Retrieves detailed information for a specific measure by name, including the full DAX expression.

Working with Tables

ListTables

Lists all tables available in the model.

GetTableDetails

Retrieves detailed information for a specific table by name.

GetTableColumns

Shows all columns for a specified table.

GetTableRelationships

Displays relationship information for a specified table.

PreviewTableData

Previews data from a table (top N rows).

Query Execution and Analysis

RunQuery

Executes a DAX query. Supports complete DAX queries with DEFINE blocks, EVALUATE statements, or simple expressions.

ValidateDaxSyntax

Validates DAX syntax and identifies potential issues with enhanced error analysis.

AnalyzeQueryPerformance

Analyzes query performance characteristics and identifies potential bottlenecks.

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "MCPBI" '{"command":"C:\\dir\\to\\mcpbi.exe","args":[]}'

See the official Claude Code MCP documentation for more details.

For Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "MCPBI": {
            "command": "C:\\dir\\to\\mcpbi.exe",
            "args": []
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Windows: %APPDATA%\Claude\claude_desktop_config.json
  • Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

{
    "mcpServers": {
        "MCPBI": {
            "command": "C:\\dir\\to\\mcpbi.exe",
            "args": []
        }
    }
}

3. Restart Claude Desktop for the changes to take effect

Want to 10x your AI skills?

Get a free account and learn to code + market your apps using AI (with or without vibes!).

Nah, maybe later