powerbi-mcp
MCP server for Power BI — local PBIX file analysis, cloud API operations, report export, and semantic model extraction from Power BI Desktop.
README
Power BI MCP Server
MCP server for Power BI — local PBIX file analysis, cloud API operations, report export, and semantic model extraction from Power BI Desktop.
45 tools • TypeScript • Cross-platform • Optimized for Pro license
⚡ Quick Start
No cloning, no building. Just add to your MCP client config:
{
"mcpServers": {
"powerbi": {
"command": "npx",
"args": ["-y", "github:AjvoGod/powerbi-mcp"],
"env": {
"POWERBI_PBIX_ROOT": "/path/to/your/pbix/files"
}
}
}
}
PBIX local analysis works immediately — no Azure credentials needed. For cloud operations (workspaces, refresh, export) add
AZURE_TENANT_ID,AZURE_CLIENT_ID,AZURE_CLIENT_SECRETtoenv.
📋 Client Configuration
Claude Desktop
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"powerbi": {
"command": "npx",
"args": ["-y", "github:AjvoGod/powerbi-mcp"],
"env": {
"POWERBI_PBIX_ROOT": "/path/to/pbix"
}
}
}
}
Gemini CLI (Google)
~/.gemini/settings.json:
{
"mcpServers": {
"powerbi": {
"command": "npx",
"args": ["-y", "github:AjvoGod/powerbi-mcp"],
"env": {
"POWERBI_PBIX_ROOT": "/path/to/pbix"
}
}
}
}
Codex CLI (OpenAI)
~/.codex/config.json:
{
"mcpServers": {
"powerbi": {
"command": "npx",
"args": ["-y", "github:AjvoGod/powerbi-mcp"],
"env": {
"POWERBI_PBIX_ROOT": "/path/to/pbix"
}
}
}
}
VS Code / Codex IDE / GitHub Copilot
Add to your project's .vscode/mcp.json or user settings:
{
"servers": {
"powerbi": {
"command": "npx",
"args": ["-y", "github:AjvoGod/powerbi-mcp"],
"env": {
"POWERBI_PBIX_ROOT": "${workspaceFolder}"
}
}
}
}
Tip: VS Code extensions like Codex IDE, Cline, Roo Code, and GitHub Copilot all support MCP servers through this same
.vscode/mcp.jsonconfiguration.
Cursor
Settings → MCP Servers → Add:
{
"mcpServers": {
"powerbi": {
"command": "npx",
"args": ["-y", "github:AjvoGod/powerbi-mcp"],
"env": {
"POWERBI_PBIX_ROOT": "/path/to/pbix"
}
}
}
}
Windsurf
Settings → MCP → Add Server:
{
"mcpServers": {
"powerbi": {
"command": "npx",
"args": ["-y", "github:AjvoGod/powerbi-mcp"],
"env": {
"POWERBI_PBIX_ROOT": "/path/to/pbix"
}
}
}
}
🔑 Access Requirements
This server is installed directly from public GitHub. Users only need:
- Node.js 20+ installed
- Git installed
No GitHub account or authentication is required!
🔧 Environment Variables
| Variable | Required | Description |
|---|---|---|
POWERBI_PBIX_ROOT |
No | Root folder containing .pbix files |
AZURE_TENANT_ID |
For cloud | Azure AD tenant ID |
AZURE_CLIENT_ID |
For cloud | Azure AD app client ID |
AZURE_CLIENT_SECRET |
For cloud | Azure AD app secret |
LOG_LEVEL |
No | Logging level: debug, info, warn, error |
With cloud credentials (optional):
{
"env": {
"POWERBI_PBIX_ROOT": "/path/to/pbix",
"AZURE_TENANT_ID": "xxxx",
"AZURE_CLIENT_ID": "xxxx",
"AZURE_CLIENT_SECRET": "xxxx"
}
}
🛠 Tools (45)
| Category | Count | Description |
|---|---|---|
| 📁 PBIX Local | 11 | Analysis, M code, layout, metadata, datasources, comparison, batch, documentation, desktop discovery, semantic model, server info |
| 📊 Dataset | 9 | List, detail, tables, sources, parameters, refresh |
| 📄 Report | 9 | List, detail, pages, export PDF/PNG/PPTX, clone, rebind, export & download |
| 🏢 Workspace | 3 | List, detail, users |
| 🔄 Dataflow | 4 | List, detail, sources, refresh |
| 🔐 Admin | 3 | Activity log, workspace scan, apps |
| 📋 Dashboard | 2 | List, tiles |
| 🌐 Gateway | 2 | List, datasources |
| ⚡ Capacity | 2 | List, workloads |
💬 Usage Examples
Without Azure credentials (PBIX analysis)
"Analyze the PBIX file Finance/Invoice Report.pbix"
"Show me the Power Query (M) code from this PBIX"
"Generate markdown documentation from all PBIX files in a folder"
"Compare these two PBIX files"
"Describe the report for intranet (Business description, Technical description, Filters, Measures sections; no tables)"
"Find running local models from Power BI Desktop"
"Extract tables and measures from the open Desktop report"
With Azure credentials (Cloud operations)
"List all workspaces"
"Trigger a refresh for dataset Y"
"Export report Z to PDF and download it"
"Show the refresh history for a dataset"
⚠️ Limitations (Pro license)
| Feature | Pro | Premium/PPU |
|---|---|---|
| REST API (list, refresh, export) | ✅ | ✅ |
| XMLA endpoint (DAX queries) | ❌ | ✅ |
| Enhanced refresh | ❌ | ✅ |
| Refresh limit | 8/day | Per capacity |
| PBIX local analysis | ✅ | ✅ |
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
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
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.