MCPJungle

<h1 align="center"> :deciduous_tree: MCPJungle :deciduous_tree: </h1> <p align="center"> Self-hosted MCP Gateway for your private AI agents </p> <p align="center"> <a href="https://discord.gg/CapV4Z3krk" style="text-decoration: none;"> <img src="https://img.shields.io/badge/Discord-MCPJungle-5865F2?style=flat-square&logo=discord&logoColor=white" alt="Discord" style="max-width: 100%;"> </a> </p> MCPJungle is a single source-of-truth registry for all [Model Context Protocol](https://modelcontextprotocol.io/introduction) Servers running in your Organisation. 🧑‍💻 Developers use it to register & manage MCP servers and the tools they provide from a central place. 🤖 MCP Clients use it to discover and consume all these tools from a single "Gateway" MCP Server.  <p align="center">MCPJungle is the only MCP Server your AI agents need to connect to!</p> # Who should use MCPJungle? 1. **Developers** using MCP Clients like Claude & Cursor that need to access MCP servers for tool-calling 2. **Developers** building production-grade AI Agents that need to access MCP servers with built-in security, privacy and Access Control. 3. **Organisations** wanting to view & manage all MCP client-server interactions from a central place. Hosted in their own datacenter 🔒 # 📋 Table of Contents - [Quick Start guide](#quickstart-guide) - [Installation](#installation) - [Usage](#usage) - [Server](#server) - [Running mcpjungle server inside Docker](#running-inside-docker) - [Running mcpjungle server directly on the host machine](#running-directly-on-host) - [Client](#client) - [Adding Streamable HTTP-based MCP servers](#registering-streamable-http-based-servers) - [Adding STDIO-based MCP servers](#registering-stdio-based-servers) - [Removing MCP servers](#deregistering-mcp-servers) - [Connect to mcpjungle from Claude](#claude) - [Connect to mcpjungle from Cursor](#cursor) - [Enabling/Disabling Tools globally](#enablingdisabling-tools) - [Prompts](#prompts) - [Tool Groups](#tool-groups) - [Authentication](#authentication) - [Enterprise features](#enterprise-features-) - [Access Control](#access-control) - [OpenTelemetry](#opentelemetry) - [Limitations](#current-limitations-) - [Contributing](#contributing-) # Quickstart guide This quickstart guide will show you how to: 1. Start the MCPJungle server locally using `docker compose` 2. Register a simple MCP server in mcpjungle 3. Connect your Claude to mcpjungle to access your MCP tools ## Start the server ```bash curl -O https://raw.githubusercontent.com/mcpjungle/MCPJungle/refs/heads/main/docker-compose.yaml docker compose up -d ``` ## Register MCP servers Download the `mcpjungle` CLI on your local machine either using brew or directly from the [Releases Page](https://github.com/mcpjungle/MCPJungle/releases). ```bash brew install mcpjungle/mcpjungle/mcpjungle ``` The CLI lets you manage everything in mcpjungle. Next, lets add an MCP server to mcpjungle using the CLI. For this example, we'll use [context7](https://context7.com/). ```bash mcpjungle register --name context7 --url https://mcp.context7.com/mcp ``` ## Connect to mcpjungle Use the following configuration for your Claude MCP servers config: ```json { "mcpServers": { "mcpjungle": { "command": "npx", "args": [ "mcp-remote", "http://localhost:8080/mcp", "--allow-http" ] } } } ``` Once mcpjungle is added as an MCP to your Claude, try asking it the following: ```text Use context7 to get the documentation for `/lodash/lodash` ``` Claude will then attempt to call the `context7__get-library-docs` tool via MCPJungle, which will return the documentation for the Lodash library. <p align="center"> <img src="./assets/quickstart-claude-call-tool.png" alt="claude calls context7 tool via mcpjungle" height="400"> </p> Congratulations! 🎉 You have successfully registered a remote MCP server in MCPJungle and called one of its tools via Claude You can now proceed to play around with the mcpjungle and explore the documentation & CLI for more details. # Installation MCPJungle is shipped as a stand-alone binary. You can either download it from the [Releases](https://github.com/mcpjungle/MCPJungle/releases) Page or use [Homebrew](https://brew.sh/) to install it: ```bash brew install mcpjungle/mcpjungle/mcpjungle ``` Verify your installation by running ```bash mcpjungle version ``` > [!IMPORTANT] > On MacOS, you will have to use homebrew because the compiled binary is not [Notarized](https://developer.apple.com/documentation/security/notarizing-macos-software-before-distribution) yet. MCPJungle provides a Docker image which is useful for running the registry server (more about it later). ```bash docker pull mcpjungle/mcpjungle ``` # Usage MCPJungle has a Client-Server architecture and the binary lets you run both the Server and the Client. ## Server The