MCP Server UniFi

A server implementation for managing and controlling UniFi network devices through MCP (Management Control Protocol). This server enables natural language interactions with your UniFi network using AI agents like Goose and Claude by wrapping the UniFi Network API.

Features

Query UniFi sites and devices using natural language through AI agents
Local server implementation that connects to your UniFi Network application
Compatible with both Goose AI and Claude Desktop
Secure API key-based authentication

Prerequisites

Python 3.8 or higher
uv package manager
UniFi Network application
UniFi API key (obtained from UniFi console)

Setup

Create an API key:
- Go to your UniFi console at https://unifi.ui.com
- Navigate to Settings » Control Plane » Integrations
- Click "Create API Key"
Clone and set up the repository:

git clone https://github.com/zcking/mcp-server-unifi
cd mcp-server-unifi
uv venv
source .venv/bin/activate  # On Unix/macOS
# or
.venv\Scripts\activate  # On Windows

Install dependencies:

uv sync

Configure environment variables:

export UNIFI_API_KEY="your_api_key_here"

Running the Server

Start the MCP development server:

uv run mcp dev main.py

The MCP Inspector will be available at http://localhost:5173 for testing and debugging.

AI Agent Integration

Goose AI Setup

Open Goose and go to Settings » Extensions » Add custom extension
Configure the extension:
- ID: unifi
- Name: unifi
- Description: Get information about your UniFi network
- Command: /Users/username/.local/bin/uv --directory /path/to/mcp-server-unifi run main.py
- Environment Variables: Set UNIFI_API_KEY to your API key

Claude Desktop Setup

Open Claude and go to Settings » Developer » Edit Config
Add to your claude_desktop_config.json:

{
    "mcpServers": {
        "unifi": {
            "command": "/Users/username/.local/bin/uv",
            "args": [
                "--directory",
                "/path/to/mcp-server-unifi",
                "run",
                "main.py"
            ]
        }
    }
}

Setup

Create an API key:

Go to your UniFi console at https://unifi.ui.com
Navigate to Settings » Control Plane » Integrations
Click "Create API Key"

Clone and set up the repository:

git clone https://github.com/zcking/mcp-server-unifi cd mcp-server-unifi uv venv source .venv/bin/activate # On Unix/macOS # or .venv\Scripts\activate # On Windows

Install dependencies:

uv sync

Configure environment variables:

export UNIFI_API_KEY="your_api_key_here"

AI Agent Integration

Goose AI Setup

Open Goose and go to Settings » Extensions » Add custom extension

Configure the extension:

ID: unifi
Name: unifi
Description: Get information about your UniFi network
Command: /Users/username/.local/bin/uv --directory /path/to/mcp-server-unifi run main.py
Environment Variables: Set UNIFI_API_KEY to your API key

Claude Desktop Setup

Open Claude and go to Settings » Developer » Edit Config

Add to your claude_desktop_config.json:

{ "mcpServers": { "unifi": { "command": "/Users/username/.local/bin/uv", "args": [ "--directory", "/path/to/mcp-server-unifi", "run", "main.py" ] } } }