Microsoft Fabric Analytics MCP Server - Python Package

Easy PyPI installation for Microsoft Fabric Analytics MCP Server

This Python package provides a convenient wrapper around the Microsoft Fabric Analytics MCP Server, enabling seamless installation and integration with AI assistants like Claude, GitHub Copilot, and other MCP-compatible clients.

🚀 Quick Start

# Install from PyPI
pip install fabric-analytics-mcp

# Start the server
fabric-analytics-mcp start

# Validate installation
fabric-analytics-mcp validate

✨ Features

• 41+ Microsoft Fabric Tools - Complete analytics toolkit
• Easy Installation - Simple pip install command
• Cross-Platform - Windows, macOS, Linux support
• Multiple Auth Methods - Bearer token, Service Principal, Interactive
• Workspace Management - Easy discovery and management
• Spark Integration - Job monitoring and session management
• Notebook Support - Execution and management
• Production Ready - Battle-tested and reliable

📋 Requirements

• Python 3.8+
• Node.js 18+ (automatically validated)
• Microsoft Fabric Access (with appropriate permissions)

🔧 Installation

Option 1: Direct PyPI Installation (Recommended)

pip install fabric-analytics-mcp

Option 2: Development Installation

git clone https://github.com/santhoshravindran7/Fabric-Analytics-MCP
cd Fabric-Analytics-MCP/python-wrapper
pip install -e .

⚙️ Configuration

Environment Variables

export FABRIC_AUTH_METHOD=bearer_token
export FABRIC_CLIENT_ID=your-client-id
export FABRIC_CLIENT_SECRET=your-client-secret  
export FABRIC_TENANT_ID=your-tenant-id
export FABRIC_DEFAULT_WORKSPACE_ID=your-workspace-id

Claude Desktop Configuration

Add to your claude_desktop_config.json:

{
  "mcpServers": {
    "fabric-analytics": {
      "command": "fabric-analytics-mcp",
      "args": ["start"],
      "env": {
        "FABRIC_AUTH_METHOD": "bearer_token"
      }
    }
  }
}

GitHub Copilot Configuration

For VS Code with GitHub Copilot:

{
  "github.copilot.mcp.servers": {
    "fabric-analytics": {
      "command": "fabric-analytics-mcp",
      "args": ["start"],
      "env": {
        "FABRIC_AUTH_METHOD": "bearer_token"
      }
    }
  }
}

🛠️ Usage

Command Line Interface

# Start the MCP server
fabric-analytics-mcp start

# Start with specific configuration
fabric-analytics-mcp start --auth-method service_principal --workspace-id <id>

# Validate installation
fabric-analytics-mcp validate

# Show configuration help
fabric-analytics-mcp config

# Get help
fabric-analytics-mcp --help

Python API

from fabric_analytics_mcp import FabricMCPServer

# Start server programmatically
config = {
    'FABRIC_AUTH_METHOD': 'bearer_token',
    'FABRIC_DEFAULT_WORKSPACE_ID': 'your-workspace-id'
}

with FabricMCPServer(config) as server:
    # Server is running
    tools = server.list_tools()
    print(f"Available tools: {len(tools['result']['tools'])}")

🏢 Available Tools

The server provides 41+ tools for Microsoft Fabric analytics:

Workspace Management

• fabric_list_workspaces - List all accessible workspaces
• fabric_find_workspace - Find workspace by name
• fabric_create_workspace - Create new workspace

Item Management

• list-fabric-items - List workspace items
• create-fabric-item - Create new items
• update-fabric-item - Update existing items
• delete-fabric-item - Delete items

Notebook Operations

• create-fabric-notebook - Create notebooks
• execute-fabric-notebook - Run notebooks
• get-fabric-notebook-definition - Get notebook content

Spark Integration

• submit-spark-job - Submit Spark jobs
• get-job-status - Monitor job status
• create-livy-session - Create interactive sessions
• execute-livy-statement - Run Spark code

Monitoring & Analytics

• get-spark-monitoring-dashboard - Performance insights
• analyze-livy-session-logs - Log analysis
• get-workspace-spark-applications - Application monitoring

View complete tool list →

🔐 Authentication

Bearer Token (Recommended for Development)

export FABRIC_AUTH_METHOD=bearer_token
# Get token from Fabric portal

Service Principal (Recommended for Production)

export FABRIC_AUTH_METHOD=service_principal
export FABRIC_CLIENT_ID=your-app-id
export FABRIC_CLIENT_SECRET=your-secret
export FABRIC_TENANT_ID=your-tenant-id

Interactive Login

export FABRIC_AUTH_METHOD=interactive
# Opens browser for authentication

🔍 Validation

Ensure everything is working correctly:

# Validate installation
fabric-analytics-mcp validate

# Test server startup
fabric-analytics-mcp start --validate

# Check tool availability
echo '{"jsonrpc": "2.0", "id": 1, "method": "tools/list"}' | fabric-analytics-mcp start

📚 Documentation

• Full Documentation
• API Reference
• Examples
• Troubleshooting

🤝 Support

• Issues: GitHub Issues
• Discussions: GitHub Discussions
• Email: santhoshravindran7@gmail.com

📄 License

This project is licensed under the MIT License - see the LICENSE file for details.

🙏 Contributing

Contributions are welcome! Please read our Contributing Guide for details.

---

Developed by Santhosh Ravindran ✨