ms-fabric-mcp-server

A Model Context Protocol (MCP) server for Microsoft Fabric. Exposes Fabric operations (workspaces, notebooks, SQL, Livy, pipelines, jobs) as MCP tools that AI agents can invoke.

⚠️ Warning: This package is intended for development environments only and should not be used in production. It includes tools that can perform destructive operations (e.g., delete_item, delete_lakehouse_file, delete_activity_from_pipeline) and execute arbitrary code via Livy Spark sessions. Always review AI-generated tool calls before execution.

Quick Start

The fastest way to use this MCP server is with uvx:

uvx ms-fabric-mcp-server

Installation

# Using uv (recommended)
uv pip install ms-fabric-mcp-server

# Using pip
pip install ms-fabric-mcp-server

# With SQL support (requires pyodbc)
pip install ms-fabric-mcp-server[sql]

# With OpenTelemetry tracing
pip install ms-fabric-mcp-server[sql,telemetry]

Authentication

Uses DefaultAzureCredential from azure-identity - no explicit credential configuration needed. This automatically tries multiple authentication methods:

1. Environment credentials (AZURE_CLIENT_ID, AZURE_TENANT_ID, AZURE_CLIENT_SECRET)

2. Managed Identity (when running on Azure)

3. Azure CLI credentials (az login)

4. VS Code credentials

5. Azure PowerShell credentials

No Fabric-specific auth environment variables are needed - it just works if you're authenticated via any of the above methods.

Usage

VS Code Integration

Add to your VS Code MCP settings (.vscode/mcp.json or User settings):

{
  "servers": {
    "MS Fabric MCP Server": {
      "type": "stdio",
      "command": "uvx",
      "args": ["ms-fabric-mcp-server"]
    }
  }
}

Claude Desktop Integration

Add to your claude_desktop_config.json:

{
  "mcpServers": {
    "fabric": {
      "command": "uvx",
      "args": ["ms-fabric-mcp-server"]
    }
  }
}

Codex Integration

Add to your Codex config.toml:

[mcp_servers.ms_fabric_mcp]
command = "uvx"
args = ["ms-fabric-mcp-server"]

Running Standalone

# Using uvx (no installation needed)
uvx ms-fabric-mcp-server

# Direct execution (if installed)
ms-fabric-mcp-server

# Via Python module
python -m ms_fabric_mcp_server

# With MCP Inspector (development)
npx @modelcontextprotocol/inspector uvx ms-fabric-mcp-server

Logging & Debugging (optional)

MCP stdio servers must keep protocol traffic on stdout, so redirect stderr to capture logs. Giving the agent read access to the log file is a powerful way to debug failures. You can also set AZURE_LOG_LEVEL (Azure SDK) and MCP_LOG_LEVEL (server) to control verbosity.

VS Code (Bash):

{
  "servers": {
    "MS Fabric MCP Server": {
      "type": "stdio",
      "command": "bash",
      "args": [
        "-lc",
        "LOG_DIR=\"$HOME/mcp_logs\"; LOG_FILE=\"$LOG_DIR/ms-fabric-mcp-$(date +%Y%m%d_%H%M%S).log\"; uvx ms-fabric-mcp-server 2> \"$LOG_FILE\""
      ],
      "env": {
        "AZURE_LOG_LEVEL": "info",
        "MCP_LOG_LEVEL": "INFO"
      }
    }
  }
}

VS Code (PowerShell):

{
  "servers": {
    "MS Fabric MCP Server": {
      "type": "stdio",
      "command": "powershell",
      "args": [
        "-NoProfile",
        "-Command",
        "$logDir=\"$env:USERPROFILE\\mcp_logs\"; New-Item -ItemType Directory -Force -Path $logDir | Out-Null; $ts=Get-Date -Format yyyyMMdd_HHmmss; $logFile=\"$logDir\\ms-fabric-mcp-$ts.log\"; uvx ms-fabric-mcp-server 2> $logFile"
      ],
      "env": {
        "AZURE_LOG_LEVEL": "info",
        "MCP_LOG_LEVEL": "INFO"
      }
    }
  }
}

Programmatic Usage (Library Mode)

from fastmcp import FastMCP
from ms_fabric_mcp_server import register_fabric_tools

# Create your own server
mcp = FastMCP("my-custom-server")

# Register all Fabric tools
register_fabric_tools(mcp)

# Add your own customizations...

mcp.run()

Configuration

Environment variables (all optional with sensible defaults):

Copy .env.example to .env and customize as needed.

Available Tools

The server provides 57 core tools, with 3 additional SQL tools when installed with [sql] extras (60 total).

SQL Tools (Optional)

SQL tools require pyodbc and the Microsoft ODBC Driver for SQL Server:

# Install with SQL support
pip install ms-fabric-mcp-server[sql]

# On Ubuntu/Debian, install the ODBC driver first:
curl https://packages.microsoft.com/keys/microsoft.asc | sudo apt-key add -
curl https://packages.microsoft.com/config/ubuntu/$(lsb_release -rs)/prod.list | sudo tee /etc/apt/sources.list.d/mssql-release.list
sudo apt-get update
sudo ACCEPT_EULA=Y apt-get install -y msodbcsql18

If pyodbc is not available, the server starts with 57 tools (SQL tools disabled).

Development

# Clone and install with dev dependencies
git clone https://github.com/your-org/ms-fabric-mcp-server.git
cd ms-fabric-mcp-server
pip install -e ".[dev,sql,telemetry]"

# Run tests
pytest

# Run with coverage
pytest --cov

# Format code
black src tests
isort src tests

# Type checking
mypy src

Integration tests

Integration tests run against live Fabric resources and are opt-in.

To get started locally, copy the example env file:

cp .env.integration.example .env.integration

Required environment variables:

• FABRIC_INTEGRATION_TESTS=1

• FABRIC_TEST_WORKSPACE_NAME

• FABRIC_TEST_LAKEHOUSE_NAME

• FABRIC_TEST_SQL_DATABASE

Optional pipeline copy inputs:

• FABRIC_TEST_SOURCE_CONNECTION_ID

• FABRIC_TEST_SOURCE_TYPE

• FABRIC_TEST_SOURCE_SCHEMA

• FABRIC_TEST_SOURCE_TABLE

• FABRIC_TEST_DEST_CONNECTION_ID

• FABRIC_TEST_DEST_TABLE_NAME (optional override; defaults to source table name)

Run integration tests:

FABRIC_INTEGRATION_TESTS=1 pytest

Notes:

• SQL tests require pyodbc and a SQL Server ODBC driver.

• Tests may skip when optional dependencies or environment variables are missing.

• These tests use live Fabric resources and may incur costs or side effects.

License

MIT