Unla

作者 AmoyLab已验证

🧩 MCP Gateway - A lightweight gateway service that instantly transforms existing MCP Servers and APIs into MCP servers with zero code changes. Features Docker deployment and management UI, requiring no infrastructure modifications.

2,210
Stars
179
Forks
TypeScript
语言
2026/8/23
添加时间

⚠️ 第三方软件声明

本 Skill 为第三方开源软件,独立托管于 GitHub。SkillTip 仅为信息目录,不控制或维护底层仓库。所显示的安全检查为自动化且范围有限,安装前请自行审查源码。

阅读服务条款

安装

添加到你的 Claude Code skills 目录:

# Add to your Claude Code skills
git clone https://github.com/AmoyLab/Unla

快速入门

使用 Unla 等 Skills 的指南。

安全报告

已验证

上次扫描:—

{
  "status": "PASSED",
  "issues": []
}

README.md

Unla - MCP Gateway

🚀 Instantly transform your existing MCP Servers and APIs into MCP endpoints — without changing a line of code.

English 简体中文 繁體中文 Release Docs Ask DeepWiki Discord Go Report Card Snyk Security LLMAPIS


Note: Unla is under rapid development! We strive to maintain backward compatibility, but it cannot be 100% guaranteed. Please make sure to check version changes carefully when upgrading. Due to the fast iteration, documentation updates may sometimes lag behind. If you encounter any issues, feel free to search or ask for help via Discord or Issues ❤️


✨ What is Unla?

Unla is a lightweight and highly available gateway service written in Go. It enables individuals and organizations to convert their existing MCP Servers and APIs into services compliant with the MCP Protocol — all through configuration, with zero code changes.

https://github.com/user-attachments/assets/69480eda-7aa7-4be7-9bc7-cae57fe16c54

🔧 Core Design Principles

  • ✅ Zero Intrusion: Platform-agnostic, supports deployment on bare metal, VMs, ECS, Kubernetes, etc., without modifying existing infrastructure
  • 🔄 Configuration-Driven: Convert legacy APIs to MCP Servers using YAML configuration — no code required
  • 🪶 Lightweight & Efficient: Designed for minimal resource usage without compromising on performance or availability
  • 🧭 Built-in Management UI: Ready-to-use web interface to simplify setup and reduce operational overhead

🚀 Getting Started

Unla supports a ready-to-run Docker deployment. Full deployment and configuration instructions are available in the docs.

Quick Launch with Docker

Configure environment variables:

export APISERVER_JWT_SECRET_KEY="changeme-please-generate-a-random-secret"
export SUPER_ADMIN_USERNAME="admin"
export SUPER_ADMIN_PASSWORD="changeme-please-use-a-secure-password"

Launch the container:

docker run -d \
  --name unla \
  -p 8080:80 \
  -p 5234:5234 \
  -p 5235:5235 \
  -p 5335:5335 \
  -p 5236:5236 \
  -e ENV=production \
  -e TZ=Asia/Shanghai \
  -e APISERVER_JWT_SECRET_KEY=${APISERVER_JWT_SECRET_KEY} \
  -e SUPER_ADMIN_USERNAME=${SUPER_ADMIN_USERNAME} \
  -e SUPER_ADMIN_PASSWORD=${SUPER_ADMIN_PASSWORD} \
  --restart unless-stopped \
  ghcr.io/amoylab/unla/allinone:latest

Access and Configuration

  1. Access the Web Interface:

  2. Add an MCP Server:

Available Endpoints

After configuration, the service will be available at these endpoints:

Configure your MCP Client with the /sse or /mcp suffix URLs to start using it.

Testing

You can test the service using:

  1. The MCP Chat page in the web interface
  2. Your own MCP Client (recommended)

📖 Read the full guide → Quick Start »


🚀 Core Features

🔌 Protocol & Proxy Capabilities

  • Support for converting RESTful APIs to MCP Server — Client → MCP Gateway → APIs
  • Support proxying MCP services — Client → MCP Gateway → MCP Servers
  • Support for converting gRPC to MCP Server — Client → MCP Gateway → gRPC
  • Support for converting WebSocket to MCP Server — Client → MCP Gateway → WebSocket
  • Support for MCP SSE
  • Support for MCP Streamable HTTP
  • Support for MCP responses including text, images, and audio

🧠 Session & Multi-Tenant Support

  • Persistent and recoverable session support
  • Multi-tenant support
  • Support for grouping and aggregating MCP servers

🛠 Configuration & Management

  • Automatic configuration fetching and seamless hot-reloading
  • Configuration persistence (Disk/SQLite/PostgreSQL/MySQL)
  • Configuration sync via OS Signals, HTTP, or Redis PubSub
  • Version control for configuration

🔐 Security & Authentication

  • OAuth-based pre-authentication support for MCP Servers

🖥 User Interface

  • Intuitive and lightweight management UI

📦 Deployment & Operations

  • Multi-replica service support
  • Docker support
  • Kubernetes and Helm deployment support

📚 Documentation

For more usage patterns, configuration examples, and integration guides, please visit:

👉 https://docs.unla.amoylab.com


📄 License

This project is licensed under the MIT License.

💬 Join Our WeChat Community

Scan the QR code below to add us on WeChat. Please include a note: mcp-gateway, mcpgw or unla.

WeChat QR Code

📈 Star History

Star History Chart

常见问题

What is Unla?

Unla is an open-source mcp servers skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by AmoyLab. 🧩 MCP Gateway - A lightweight gateway service that instantly transforms existing MCP Servers and APIs into MCP servers with zero code changes. Features Docker deployment and management UI, requiring no infrastructure modifications. It has 2,210 GitHub stars.

Is Unla safe to use?

Yes. Unla passed SkillsLLM's automated security scan — a dependency vulnerability audit plus prompt-injection heuristics — with no high-severity issues. You can read the full report in the Security Report section on this page.

How do I install Unla?

Clone the repository with "git clone https://github.com/AmoyLab/Unla" and add it to your Claude Code skills directory (see the Installation section above).

What programming language is Unla written in?

Unla is primarily written in TypeScript. It is open-source under AmoyLab on GitHub, so you can review or fork the full source.

Are there alternatives to Unla?

Yes. SkillsLLM lists many other MCP Servers skills you can browse and compare side by side. Open the MCP Servers category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh Unla against similar tools.

评论 (0)

暂无评论,成为第一个分享想法的人!

n8n

by n8n-io

12

Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.

201,88160,308TypeScript
MCP 服务器apisai-tools
查看详情

Scrapling

by D4Vinci

🕷️ An adaptive Web Scraping framework that handles everything from a single request to a full-scale crawl!

75,9137,581Python
MCP 服务器
查看详情

TrendRadar

by sansan0

⭐AI-driven public opinion & trend monitor with multi-platform aggregation, RSS, and smart alerts.🎯 告别信息过载,你的 AI 舆情监控助手与热点筛选工具!聚合多平台热点 + RSS 订阅,支持关键词精准筛选。AI 智能筛选新闻 + AI 翻译 + AI 分析简报直推手机,也支持接入 MCP 架构,赋能 AI 自然语言对话分析、情感洞察与趋势预测等。支持 Docker ,数据本地/云端自持。集成微信/飞书/钉钉/Telegram/邮件/ntfy/bark/slack 等渠道智能推送。

61,65224,883Python
MCP 服务器
查看详情

context7

by upstash

Context7 Platform -- Up-to-date code documentation for LLMs and AI code editors

61,0602,938TypeScript
MCP 服务器
查看详情

High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 158 languages, sub-ms queries, 99% fewer tokens. Single static binary, zero dependencies.

39,9393,219C
MCP 服务器
查看详情

开发者还喜欢

基于喜欢此 Skill 的开发者投票和收藏

ECC

by affaan-m

10

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

242,21936,702JavaScript
AI 智能体ai-agentsanthropicclaude-code
查看详情
15

An agentic skills framework & software development methodology that works.

234,96620,863Shell
AI 智能体ai-agentsbrainstorming
查看详情

hermes-agent

by NousResearch

10

The agent that grows with you

234,43747,175Python
AI 智能体ai-agentsagent-orchestration
查看详情

n8n

by n8n-io

12

Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.

201,88160,308TypeScript
MCP 服务器apisai-tools
查看详情

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

185,94028,768JavaScript
AI 智能体ai-agentsanthropicclaude-code
查看详情

cc-switch

by farion1231

3

A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Grok Build & Hermes Agent. Only official website: ccswitch.io

128,8688,826Rust
AI 智能体claude-codeai-tools
查看详情