UniFi MCP Server
Enables MCP-capable clients to interact with UniFi Site Manager and UniFi Dream Machine telemetry, providing tools for client details, ISP metrics, and more.
README
UniFi MCP Server
[!IMPORTANT] This software is a personal project that I'm releasing via the MIT License. Furthermore, this project has no affiliation with Ubiquiti, Inc. UniFi, UniFi Dream Machine, and UniFi Site Manager are registered trademarks of Ubiquiti Inc.
[!WARNING] This MCP server should be considered early beta. I don't plan on introducing any breaking changes, but please keep in mind that it may nonetheless twitch a little between updates. Tools will be added as the UniFi SM and Network APIs mature, but more realistically as often as time permits on my side.
About This Project
This MCP server's intended use is to allow MCP-capable clients (e.g., Claude Desktop) to directly interact with UniFi Site Manager and UniFi Dream Machine and make the available telemetry usable in a conversational context. It has not been tested outside of this scope (but it's probably fine).
This server provides the following tools:
- mcpGetClientDetails
- mcpGetClients
- mcpGetISPMetrics
- mcpGetDateAndTime
- mcpPing
Schema and decriptions for each tool are documented in their respective files. Test coverage is available for observation/validation purposes.
[!TIP] A Dockerfile is provided and has been tested in Podman. This is the recommended approach to running the server.
API Keys
Instructions for obtaining API keys are in the sample.env file. It's beyond the scope of this project to dictate how you manage these secrets. The JSON blob provided below is obviously the fastest way to get started, but you're encouraged to handle these keys in a way that is in accordance with your policies, or, more bluntly, in a way that doesn't keep you up at night.
JSON configuration for your MCP client
{
"mcp-unifi": {
"command": "<path/to/podman>",
"args": [
"run",
"--rm",
"-i",
"--env-file",
"<path/to/.env>",
"mcp-unifi:latest"
]
}
}
Statement on AI
This project was pair-programmed with Claude Code. Claude wrote the unit tests, Dockerfile, and assisted with answering the odd question I had about the inner-workings of the MCP SDK.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.