MCP Server for Netwrix Access Analyzer
About
A FastMCP-based server that connects to Netwrix Access Analyzer databases, enabling data analysis through Claude Desktop. It provides tools for SQL Server connectivity, schema exploration, and access analysis of file system data.
Details
- License
- MIT license
Explore
- SQL Server integration with automatic connection on startup
- Dynamic database schema exploration
- SQL query execution
- Netwrix Access Analyzer File System tools
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
MCP Server for Netwrix Access AnalyzerCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
For development or testing purposes only:
1. Create a .env file in your project directory with your SQL Server connection details:
json
"NetwrixAccessAnalyzer": {
"command": "/path/to/your/uv",
"args": [
"run",
"--with",
"pyodbc,fastmcp",
"fastmcp",
"run",
"/path/to/mcp/main.py"
],
"env": {
"DB_SERVER": "your_server_address",
"DB_NAME": "your_database_name",
"DB_USER": "your_username",
"DB_PASSWORD": "your_password",
"DB_USE_WINDOWS_AUTH": "FALSE"
}
}
``
1. Replace
/path/to/your/uv with the actual path to your uv executable (find with which uv or where uv), and update the path to your main.py` file as well as the database connection information.2. Restart Claude Desktop to apply the changes
Check currently running Netwrix Access Analyzer jobs.
Example prompt:
"Are there any Access Analyzer jobs running right now? Show me the status."
The MCP server provides the following tools for interacting with database systems and analyzing access data:
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"mcp server for netwrix access analyzer": {
"NetwrixAccessAnalyzer": {
"command": "uv",
"args": [
"run",
"--with",
"pyodbc,fastmcp",
"fastmcp",
"run",
"/path/to/mcp/main.py"
],
"env": {
"DB_SERVER": "",
"DB_NAME": "",
"DB_USER": "",
"DB_PASSWORD": "",
"DB_USE_WINDOWS_AUTH": ""
}
}
}
}
}
McpServers
{
"NetwrixAccessAnalyzer": {
"command": "uv",
"args": [
"run",
"--with",
"pyodbc,fastmcp",
"fastmcp",
"run",
"/path/to/mcp/main.py"
],
"env": {
"DB_SERVER": "",
"DB_NAME": "",
"DB_USER": "",
"DB_PASSWORD": "",
"DB_USE_WINDOWS_AUTH": ""
}
}
}
A FastMCP-based server for Netwrix Access Analyzer data analysis, designed to integrate with Claude Desktop for enhanced data analysis capabilities.
Features
- SQL Server integration with automatic connection on startup
- Dynamic database schema exploration
- SQL query execution
- Netwrix Access Analyzer File System tools
Dependencies
This MCP server requires the following dependencies:
- Python 3.12 or higher
- MCP SDK
- pyodbc 4.0.39 or higher (for SQL Server connectivity)
- python-dotenv 1.0.0 or higher (for environment variable management)
- ODBC Driver 17 for SQL Server or later (must be installed on your system)
Netwrix Access Analyzer (NAA) Dependencies
This MCP Server requires Netwrix Access Analyzer (NAA) File System scans to be completed.
Installation
System Dependencies
First, ensure you have the ODBC Driver for SQL Server installed:
- macOS: Install using Homebrew: brew install microsoft/mssql-release/msodbcsql17
- Windows: Download and install from the Microsoft ODBC Driver page
- Linux: Follow Microsoft's instructions for your distribution
Python Dependencies
Install required Python packages using uv
Database Setup
For development or testing purposes only:
1. Create a .env file in your project directory with your SQL Server connection details:
```
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.



