Power BI Modeling MCP SSE Bridge
This MCP server provides a web-ready SSE bridge for Microsoft's Power BI Modeling MCP Server, enabling URL-based interaction with Power BI semantic models from any programming language without local stdio piping. It features automatic Azure authentication and dynamic binary resolution for seamless Power BI data analysis.
README
Power BI Modeling MCP SSE Bridge
This project is a high-performance SSE (Server-Sent Events) Bridge for the Official Microsoft Power BI Modeling MCP Server. It enables seamless, URL-based interaction with Power BI semantic models from any language (Laravel, Python, Go) without the need for local stdio piping.
🔥 Key Innovations
- Auto-Auth (Token Injection): Automatically performs an Azure ROPC flow using your Admin credentials to inject an Access Token. Result: Zero browser popups on your server.
- Dynamic Binary Resolution: Automatically detects your OS and CPU architecture to spawn the correct Microsoft MCP binary.
- Laravel Context Injection: Pass Workspace and Dataset IDs via URL query parameters to maintain session-specific contexts.
- Web-Ready: Perfect for building custom AI Chat interfaces for Power BI.
🛠️ Installation & Quick Start
1. Requirements
- Node.js v18 or higher.
- Power BI Admin account (Master User) or Service Principal.
2. Setup
git clone https://github.com/nusagates/mcp_pbi.git
cd mcp_pbi
npm install
3. Configuration
Create a .env file from the template:
cp .env.example .env
Fill in your MS_PBI_... credentials. Important: For the password-based login to work without a browser, enable "Allow public client flows" in your Azure App Registration -> Authentication settings.
4. Run
npm start
The bridge will be live at http://localhost:3000/sse.
🔗 Laravel Integration Example
Using Laravel's Http facade to interact with the bridge:
use Illuminate\Support\Facades\Http;
// 1. Establish connection context (via Browser/SSE Client)
// URL: http://localhost:3000/sse?workspace_id=abc&dataset_id=123
// 2. Execute a Tool through the bridge
$response = Http::post("http://localhost:3000/messages?sessionId=YOUR_SESSION_ID", [
"jsonrpc" => "2.0",
"id" => 1,
"method" => "tools/call",
"params" => [
"name" => "execute_dax_query",
"arguments" => [
"query" => "EVALUATE TOPN(10, 'YourTable')"
]
]
]);
return $response->json();
🛡️ Power BI Permissions Checklist
- [ ] Azure Portal: App Registration exists with
Tenant.Read.All. - [ ] Power BI Admin: "Allow service principals to use Power BI APIs" is ON.
- [ ] Workspace: App or User is added as a Member/Contributor.
🤝 Credits
This bridge uses the Microsoft Power BI Modeling MCP Server as its core engine. Special thanks to the Microsoft team for the protocol implementation.
📄 License
MIT License. Feel free to use and contribute!
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.