datumnova/ms-fabric-mcp

A comprehensive Python-based MCP (Model Context Protocol) server for interacting with Microsoft Fabric APIs, featuring advanced PySpark notebook development, testing, and optimization capabilities with LLM integration.
🚀 Features
**Core Fabric Operations**
- ✅ Workspace, lakehouse, warehouse, and table management
- ✅ Delta table schemas and metadata retrieval
- ✅ SQL query execution and data loading
- ✅ Report and semantic model operations
**Advanced PySpark Development**
- 📓 **Intelligent notebook creation** with 6 specialized templates
- 🔧 **Smart code generation** for common PySpark operations
- ✅ **Comprehensive validation** with syntax and best practices checking
- 🎯 **Fabric-specific optimizations** and compatibility checks
- 📊 **Performance analysis** with scoring and optimization recommendations
- 🚀 **Real-time monitoring** and execution insights
**LLM Integration**
- 🤖 **Natural language interface** for PySpark development
- 🧠 **Context-aware assistance** with conversation memory
- 🎨 **Intelligent code formatting** and explanations
- 📈 **Smart optimization suggestions** based on project patterns
🏗️ Architecture
**Interaction Flow**
1. **Developer requests assistance in IDE**
2. **IDE communicates with LLM (Claude/GPT)**
3. **LLM analyzes using context and reasoning**
4. **LLM calls MCP server tools intelligently**
5. **MCP tools interact with Fabric API**
6. **Results flow back through LLM with intelligent formatting**
7. **Developer receives contextual, smart responses**
📋 Requirements
- **Python 3.12+**
- **Azure credentials** for authentication
- **uv** (from astral): Installation instructions
- **Azure CLI**: Installation instructions
- **Optional: Node.js** for MCP inspector: Installation instructions
🔧 Installation
1. **Clone the repository:**
2. **Set up virtual environment:**
3. **Install dependencies:**
🚀 Usage
1. **Using STDIO**
**Connect to Microsoft Fabric**
**Running with MCP Inspector**
This starts the server with inspector at http://localhost:6274.
**VSCode Integration**
Add to your launch.json:
2. **Using HTTP**
**Start the MCP Server**
**VSCode Integration**
Add to your launch.json:
🛠️ Complete Tool Reference
**1. Workspace Management**
list_workspaces
List all available Fabric workspaces.
set_workspace
Set the current workspace context for the session.
**2. Lakehouse Operations**
list_lakehouses
List all lakehouses in a workspace.
create_lakehouse
Create a new lakehouse.
set_lakehouse
Set current lakehouse context.
**3. Warehouse Operations**
list_warehouses
List all warehouses in a workspace.
create_warehouse
Create a new warehouse.
set_warehouse
Set current warehouse context.
**4. Table Operations**
list_tables
List all tables in a lakehouse.
get_lakehouse_table_schema
Get schema for a specific table.
get_all_lakehouse_schemas
Get schemas for all tables in a lakehouse.
set_table
Set current table context.
**5. SQL Operations**
get_sql_endpoint
Get SQL endpoint for lakehouse or warehouse.
run_query
Execute SQL queries.
**6. Data Loading**
load_data_from_url
Load data from URL into tables.
**7. Reports & Models**
list_reports
List all reports in a workspace.
get_report
Get specific report details.
list_semantic_models
List semantic models in workspace.