home / mcp / pbixray mcp server
MCP server to give llms such as Claude, GitHub Copilot etc full PowerBI model context (from input .pbix) through tools based on PBIXRay python package.
Configuration
View docs{
"mcpServers": {
"jonaolden-pbixray-mcp-server": {
"command": "wsl.exe",
"args": [
"bash",
"-c",
"source ~/dev/pbixray-mcp/venv/bin/activate && python ~/dev/pbixray-mcp/src/pbixray_server.py"
]
}
}
}You can run the PBIXRay MCP Server to expose Power BI PBIX file analysis as MCP tools for large language model clients. This server lets you load PBIX files, explore the data model, view M and DAX code, inspect model metadata, and paginate table contents, all through a consistent MCP interface.
You will connect to the PBIXRay MCP Server from an MCP client. Once connected, you can load a PBIX file, list the tables in the model, inspect metadata and statistics, view Power Query (M) code and parameters, explore DAX calculated tables, measures, and columns, and retrieve schema details and table contents with pagination. Use the available tools to compose queries that retrieve exactly the data you need, then paginate results as necessary to manage large tables.
Your MCP client can enable or disable individual tools to control what information is exposed. This is useful if you want to limit sensitive data or only expose features you rely on.
Prerequisites: Python must be installed on your system. If you plan to run the server under Windows Subsystem for Linux (WSL), ensure WSL is installed and configured.
Install the PBIXRay MCP Server package for development or runtime use with Pythonβs package manager.
Install the server as a Python package.
Configure your client to connect to the MCP server using the following stdio configuration (local server). This example uses WSL to run the server.
{
"mcpServers": {
"pbixray": {
"command": "wsl.exe",
"args": [
"bash",
"-c",
"source ~/dev/pbixray-mcp/venv/bin/activate && python ~/dev/pbixray-mcp/src/pbixray_server.py"
]
}
}
}You can also start the server directly via a development command if you are working locally. The server is designed to be run inside a development environment where you activate a virtual environment and start the Python script for the MCP server.
If you are using Claude Desktop or a similar MCP client, you can place the same command in your clientβs configuration to start the PBIXRay MCP Server through WSL.
Load a Power BI (.pbix) file for analysis.
List all tables in the model.
Get metadata about the Power BI configuration.
Display all M/Power Query code used for data transformation.
Display all M Parameters values.
Get the model size in bytes.
View DAX calculated tables.
Access DAX measures with filtering by table or measure name.
Access calculated column DAX expressions with filtering options.
Get details about the data model schema and column types.
Get the details about the data model relationships.
Retrieve the contents of a specified table with pagination.
Get statistics about the model with optional filtering.
Get a comprehensive summary of the current Power BI model.