enuno/unifi-mcp-server

What it solves

Managing UniFi network infrastructure often requires manual navigation through complex web interfaces. This project provides a standardized way for AI agents to interact with UniFi hardware, allowing them to read network data, adjust configurations, and manage devices automatically through the Model Context Protocol (MCP).

How it works

The server acts as a bridge between an AI client (like Claude Desktop or Cursor) and your UniFi controller. It exposes hundreds of specific tools—such as those for network settings, firewall rules, camera management, and device diagnostics—as standardized commands. You can run it in 'local' mode to control your own hardware or connect to UniFi cloud APIs for aggregate site management. It includes safety features like mandatory confirmation for changes, dry-run modes, and role-based access control.

Who it’s for

This tool is designed for network administrators, home lab enthusiasts, and developers who want to automate their UniFi infrastructure using AI. It is particularly useful for those who want to perform complex tasks like auditing firewall rules, planning WiFi channels, or managing multi-site deployments through natural language prompts.

Highlights

• Offers over 300 tools for comprehensive control over UniFi Network, Protect, and cloud services.
• Supports 'Fleet Mode' for managing multiple controllers from a single interface with centralized logging and caching.
• Built-in safety mechanisms including audit logs, dry-run capabilities, and risk-tier-based access control.
• Provides specialized 'Agent Skills' (Markdown files) that help AI agents understand and execute network tasks effectively.
• Highly observable with support for Prometheus metrics, SIEM export, and webhook integration.