Unifi MCP Server
@enuno
About Unifi MCP Server
An MCP server that leverages official UniFi API
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"unifi": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"UNIFI_API_KEY=$API_KEY",
"-e",
"UNIFI_API_TYPE=cloud",
"ghcr.io/enuno/unifi-mcp-server:latest"
]
}
}
}Tools
No tools detected
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Overview
What is Unifi MCP Server?
A Model Context Protocol (MCP) server that exposes the UniFi Network Controller API and is evolving into a multi-domain platform for Protect, Access, and enterprise-scale orchestration. It is designed for network operators and developers who need programmatic control over UniFi infrastructure.
How to use Unifi MCP Server?
Install via pip: pip install unifi-mcp-server. Set environment variables for API mode (e.g., UNIFI_API_TYPE=local) and transport (e.g., MCP_SERVER_TRANSPORT=stdio), then run unifi-mcp-server. For SSE mode, set MCP_SERVER_TRANSPORT=sse and expose a port.
Key features of Unifi MCP Server
- Device management (list, restart, locate, upgrade)
- Network, VLAN, DHCP, and WiFi configuration
- Client management with block/unblock and analytics
- Port profile and switch port configuration
- Firewall rules and ACL management
- Multi-site aggregation and cross-site statistics
- 220+ async tool functions across 40+ modules
Use cases of Unifi MCP Server
- Automate network configuration and updates across sites
- Monitor device, client, and bandwidth statistics in real time
- Manage firewall rules and access control lists programmatically
- Integrate UniFi management with AI assistants via MCP transport
- Orchestrate multi-site deployments with dry-run and audit logging
FAQ from Unifi MCP Server
What API modes are supported?
Three modes: Local Gateway API (full feature, read-write), Cloud Early Access API (site-only, read-only, 100 req/min), and Cloud V1 API (aggregate statistics only, read-only, 10,000 req/min). Recommendation: use Local Gateway API.
What transport modes are available?
STDIO (default for local subprocess), SSE (network-accessible HTTP), HTTP, and Streamable HTTP. SSE is best for MCP gateways, STDIO for Claude Desktop and Cursor.
What are the runtime requirements?
Python 3.10 or later. Install via pip install unifi-mcp-server. For local API, network access to the UniFi gateway (e.g., 192.168.2.1) is required.
Where does the server store data?
The server does not store data locally; it communicates with the UniFi controller's API. All device, client, and configuration data resides on the UniFi controller.
What are the known limitations of cloud API modes?
Cloud EA and Cloud V1 modes are read-only; they cannot query individual devices or clients, and cannot make configuration changes. They are suitable only for high-level monitoring dashboards.
Frequently asked questions
What API modes are supported?
Three modes: Local Gateway API (full feature, read-write), Cloud Early Access API (site-only, read-only, 100 req/min), and Cloud V1 API (aggregate statistics only, read-only, 10,000 req/min). Recommendation: use Local Gateway API.
What transport modes are available?
STDIO (default for local subprocess), SSE (network-accessible HTTP), HTTP, and Streamable HTTP. SSE is best for MCP gateways, STDIO for Claude Desktop and Cursor.
What are the runtime requirements?
Python 3.10 or later. Install via `pip install unifi-mcp-server`. For local API, network access to the UniFi gateway (e.g., 192.168.2.1) is required.
Where does the server store data?
The server does not store data locally; it communicates with the UniFi controller's API. All device, client, and configuration data resides on the UniFi controller.
What are the known limitations of cloud API modes?
Cloud EA and Cloud V1 modes are read-only; they cannot query individual devices or clients, and cannot make configuration changes. They are suitable only for high-level monitoring dashboards.
Basic information
More Other MCP servers
Maestro
mobile-dev-incPainless E2E Automation for Mobile and Web
MCP Go π
mark3labsA Go implementation of the Model Context Protocol (MCP), enabling seamless integration between LLM applications and external data sources and tools.
Inbox Zero AI
elie222The world's best AI personal assistant for email. Open source app to help you reach inbox zero fast.
Production-ready MCP integrations for AI applications
Klavis-AIKlavis AI: MCP integration platforms that let AI agents use tools reliably at any scale
MCP Registry
modelcontextprotocolA community driven registry service for Model Context Protocol (MCP) servers.
Comments