PBIXRay

Exposes a PBIX Power BI model to MCP clients for loading, exploring, and querying data through tools like get_tables, get_schema, and get_table_contents.

python

GitHub Stars

python

Language

6 months ago

First Indexed

3 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "guyensoto-pbixray-mcp-server-for-git": {
      "command": "D:\\AI\\Guyen\\pbixray-mcp-server-main\\.venv\\Scripts\\python.exe",
      "args": [
        "D:\\AI\\Guyen\\pbixray-mcp-server-main\\src\\pbixray_server.py"
      ],
      "env": {
        "PYTHONPATH": "D:\\Projects\\pbixray-mcp-server-main"
      }
    }
  }
}

PBIXRay MCP Server lets you expose a Power BI .pbix model to clients via the Model Context Protocol (MCP). You can load PBIX files, explore the data model, inspect Power Query and DAX expressions, and retrieve structured data like schema, relationships, and table contents through a configurable MCP server. This makes it easy to drive LLMs and automation against your Power BI assets without manual inspection of the model files.

How to use

Start the server as a local MCP endpoint and connect your MCP client to it. Load a PBIX file, then use the available tools to list tables, view metadata, inspect M code and DAX expressions, and fetch table contents with pagination. You can disable specific tools for security and tailor the server capabilities to your needs.

How to install

Prerequisites you need to prepare before running the server:

Python 3.13 is recommended (minimum 3.10+)
uv package manager
Windows PowerShell

First time setup and running the server as a local MCP (stdio)

D:\AI\Guyen\pbixray-mcp-server-main\.venv\Scripts\python.exe
D:\AI\Guyen\pbixray-mcp-server-main\src\pbixray_server.py

Verification and startup tips

After installing dependencies and verifying your Python version, activate the virtual environment and start the MCP server using the exact runtime command shown above. Then verify that the server starts by checking the console for a successful startup message and proceed to load a PBIX file to begin exploration.

Configuring the MCP client to connect to PBIXRay

You will connect to PBIXRay via a local stdio MCP entry. The complete command to run the server locally is shown in the previous step. Your MCP client should reference this stdio entry to start the server and then use the available MCP tools to interact with the loaded PBIX model.

Available tools

load_pbix_file

Load a Power BI (.pbix) file into the MCP server for analysis.

get_tables

List all tables available in the loaded Power BI data model.

get_metadata

Retrieve metadata about the Power BI configuration for the loaded model.

get_power_query

Display all M/Power Query code used for data transformation in the model.

get_m_parameters

Display all M Parameters and their values.

get_model_size

Get the size of the loaded model in bytes.

get_dax_tables

View DAX calculated tables present in the model.

get_dax_measures

Access DAX measures with optional filtering by table or measure name.

get_dax_columns

Access calculated column DAX expressions with optional filtering.

get_schema

Get details about the data model schema and column types.

get_relationships

Get details about the data model relationships.

get_table_contents

Retrieve contents of a specified table with pagination.

get_statistics

Get statistics about the model with optional filtering.

get_model_summary

Get a comprehensive summary of the current Power BI model.

Built by

VeilStrat

AI signals for GTM teams