MM

mcpjungle/mcpjungle

部署与 DevOps

本页由 AI 翻译,技术细节请以原文为准。 查看原文

1530 stars 194 forks 质量 89 趋势 89MPL-2.0

一个管理并连接所有MCP服务器的地方

概览

MCPJungle 将所有MCP服务器运行在一个端点之下 MCPJungle 是一个自架的 MCP 网关,面向希望管理多个 MCP 服务器且不涉及分散客户端配置、重复设置或访问控制不一致的开发者和团队。 用它来保持个人MCP的整洁,或者像团队一样运行,同时拥有集中式的发现、访问控制和可观察性。 与其把每个MCP服务器都接到每个AI客户端,不如先在MCPJungle注册一次服务器,让Claude、Cursor、Codex或你自己的代理连接到单一MCP端点。 MCP功能强大,但管理大量MCP服务器很快就会变得一团糟。

概述(AI 翻译)

MCPJungle

把所有MCP服务器都放在一个端点后面

MCPJungle 是一个自架的 MCP 网关,面向希望管理多个 MCP 服务器且不涉及分散客户端配置、重复设置或访问控制不一致的开发者和团队。

你可以本地使用它来保持个人MCP的整洁,或者作为共享基础设施运行给团队,拥有集中式的发现、访问控制和可观察性。

与其把每个MCP服务器都接到每个AI客户端,不如先在MCPJungle注册一次服务器,让Claude、Cursor、Codex或你自己的代理连接到单一MCP端点。

为什么是MCPJungle?

MCP功能强大,但管理大量MCP服务器很快就会变得一团糟。

没有网关:

  • 🔌 每个客户端都需要自己的MCP服务器配置
  • 🧩 工具、提示和资源分散在不同服务器上
  • 🔐 访问控制重复或缺失
  • 👥 Teams 没有共享可用的 MCP 工具视图
  • 🛠️ 局部设置变得难以复现

MCPJungle给你一个控制点:

  • 🌐 一个MCP端点,用于Claude、Cursor、Copilot和自定义代理
  • 🗂️ 一个注册和管理MCP服务器的地方

本页由 AI 翻译,技术细节请以原文为准。

README

以下为原文 README 节选,完整内容请查看原文。

MCPJungle

Run all your MCP servers behind one endpoint

MCPJungle is a self-hosted MCP gateway for developers and teams who want to manage multiple MCP servers without scattered client configurations, duplicated setup, or inconsistent access control.

Use it locally to keep your personal MCP setup clean, or run it as shared infrastructure for a team with centralized discovery, access control, and observability.

Instead of wiring every MCP server into every AI client, register your servers once in MCPJungle and let Claude, Cursor, Codex, or your own Agents connect to a single MCP endpoint.

Why MCPJungle?

MCP is powerful, but managing many MCP servers gets messy fast.

Without a gateway:

  • 🔌 Every client needs its own MCP server configuration
  • 🧩 Tools, prompts, and resources are scattered across different servers
  • 🔐 Access control is duplicated or missing
  • 👥 Teams have no shared view of available MCP tools
  • 🛠️ Local setups become hard to reproduce

MCPJungle gives you a single control point:

  • 🌐 One MCP endpoint for Claude, Cursor, Copilot, and custom agents
  • 🗂️ One place to register and manage MCP servers
  • 🔎 Unified discovery for tools, prompts, and resources
  • 🎛️ Optional tool groups to expose only the tools a client should see
  • 📊 Simple access-control and observability hooks for shared deployments

Start with a local setup. Scale to a shared team gateway when you need it.

Documentation

Mcpjungle documentation has a new home: https://docs.mcpjungle.com.

Please prefer the docs site over this README for the latest guides, reference, and operational details.

Your AI Clients can also access the docs using its MCP server https://docs.mcpjungle.com/mcp!

Quickstart

This quickstart guide will show you how to:

  1. Start the mcpjungle server locally using docker compose
  2. Add an MCP server in mcpjungle
  3. Connect your Claude Desktop to mcpjungle to access your MCP tools

Start the server

在 GitHub 查看完整 README

安装

npx mcp-remote http://localhost:8080/mcp --allow-http
新手?先看 mcpskill.org 教程 →

配置

{ "mcpServers": { "mcpjungle": { "command": "npx", "args": [ "mcp-remote", "http://localhost:8080/mcp", "--allow-http" ] } } }