Skip to main content
Glama
enesjakozh

MCP Server UniFi

by zcking
GitHub
Python
MIT License
  • Apple
  • Linux
OverviewInspectNewSchemaRelated ServersReviewsScore
Need Help?View Source CodeReport Issue

MCP 服务器 UniFi

通过 MCP（管理控制协议）管理和控制 UniFi 网络设备的服务器实现。该服务器通过封装 UniFi 网络 API，使用 Goose 和 Claude 等 AI 代理与您的 UniFi 网络进行自然语言交互。

特征

  • 通过 AI 代理使用自然语言查询 UniFi 站点和设备
  • 连接到您的 UniFi 网络应用程序的本地服务器实现
  • 兼容 Goose AI 和 Claude Desktop
  • 基于安全 API 密钥的身份验证

先决条件

  • Python 3.8 或更高版本
  • uv包管理器
  • UniFi 网络应用
  • UniFi API 密钥（从 UniFi 控制台获取）

设置

  1. 创建 API 密钥：
    • 前往您的 UniFi 控制台https://unifi.ui.com
    • 导航至“设置”»“控制平面”»“集成”
    • 点击“创建 API 密钥”
  2. 克隆并设置存储库：
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
  1. 安装依赖项：
uv sync
  1. 配置环境变量：
export UNIFI_API_KEY="your_api_key_here"

运行服务器

启动 MCP 开发服务器：

uv run mcp dev main.py

MCP Inspector 可在http://localhost:5173上进行测试和调试。

AI代理集成

Goose AI 设置

  1. 打开 Goose 并转到“设置”»“扩展”»“添加自定义扩展”
  2. 配置扩展：
    • ID：unifi
    • 名称：unifi
    • 描述：获取有关您的 UniFi 网络的信息
    • 命令： /Users/username/.local/bin/uv --directory /path/to/mcp-server-unifi run main.py
    • 环境变量：将 UNIFI_API_KEY 设置为您的 API 密钥

Claude 桌面设置

  1. 打开 Claude 并转到设置»开发者»编辑配置
  2. 添加到您的claude_desktop_config.json ：
{ "mcpServers": { "unifi": { "command": "/Users/username/.local/bin/uv", "args": [ "--directory", "/path/to/mcp-server-unifi", "run", "main.py" ] } } }

This server cannot be installed

-
security - not tested
A
license - permissive license
-
quality - not tested

How are these scores calculated?

hybrid server

The server is able to function both locally and remotely, depending on the configuration or use case.

一种服务器实现，通过为 Goose 和 Claude 等 AI 代理包装 UniFi 网络 API，实现与 UniFi 网络设备的自然语言交互。

  1. 特征
    1. 先决条件
      1. 设置
        1. 运行服务器
          1. AI代理集成
            1. Goose AI 设置
            2. Claude 桌面设置

          Related MCP Servers

          • Model Context Protocol (MCP) Server

            hideya
            -
            security
            A
            license
            -
            quality
            This server facilitates the invocation of AI models from providers like Anthropic, OpenAI, and Groq, enabling users to manage and configure large language model interactions seamlessly.
            Last updated -
            9
            Python
            MIT License

          • ServiceNow MCP Server

            michaelbuckner
            -
            security
            A
            license
            -
            quality
            A Model Context Protocol server enabling AI agents to access and manipulate ServiceNow data through natural language interactions, allowing users to search for records, update them, and manage scripts.
            Last updated -
            9
            Python
            MIT License

          • ClickUp MCP Server

            windalfin
            -
            security
            A
            license
            -
            quality
            A Model Context Protocol server that enables AI agents to interact with ClickUp workspaces, allowing task creation, management, and workspace organization through natural language commands.
            Last updated -
            605
            MIT License

          • MCP Server for Asana

            cristip73
            -
            security
            A
            license
            -
            quality
            This server implementation allows AI assistants to interact with Asana's API, enabling users to manage tasks, projects, workspaces, and comments through natural language requests.
            Last updated -
            189
            TypeScript
            MIT License

          View all related MCP servers

          Appeared in Searches

          New MCP Servers

          MCP directory API

          We provide all the information about MCP servers via our MCP API.

          curl -X GET 'https://glama.ai/api/mcp/v1/servers/zcking/mcp-server-unifi'

          If you have feedback or need assistance with the MCP directory API, please join our Discord server