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 | ✅ | ✅ |
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。