{"name":"MCPJungle: Self-Hosted MCP Gateway for AI Agents and Tool Management","description":"MCPJungle is an open-source, self-hosted Model Context Protocol (MCP) Gateway designed for managing AI agents and their tool-calling capabilities. It allows developers and organizations to centralize the registration, discovery, and consumption of MCP servers and their tools, enhancing security and control over AI agent interactions.","github":"https://github.com/mcpjungle/MCPJungle","url":"https://osrepos.com/repo/mcpjungle-mcpjungle","source":"osrepos.com","sourceDescription":"This repository profile is provided by osrepos.com, an open source repository discovery platform.","repositoryProfile":"https://osrepos.com/repo/mcpjungle-mcpjungle","generatedFor":"open source discovery and AI-assisted research","markdown":"https://osrepos.com/repo/mcpjungle-mcpjungle.md","json":"https://osrepos.com/repo/mcpjungle-mcpjungle.json","topics":["ai-agents","llmops","mcp-gateway","self-hosted","Go","infrastructure","tool-calling"],"keywords":["ai-agents","llmops","mcp-gateway","self-hosted","Go","infrastructure","tool-calling"],"stars":null,"summary":"MCPJungle is an open-source, self-hosted Model Context Protocol (MCP) Gateway designed for managing AI agents and their tool-calling capabilities. It allows developers and organizations to centralize the registration, discovery, and consumption of MCP servers and their tools, enhancing security and control over AI agent interactions.","content":"## Introduction\n\nMCPJungle is an open-source, self-hosted Model Context Protocol (MCP) Gateway built in Go, designed to centralize the management of AI agents and their tool-calling capabilities. It acts as a unified gateway for your private AI agents, allowing you to register and manage various MCP servers and the tools they provide from a single, secure location. This enhances security, privacy, and access control for your AI agent interactions.\n\n## Installation\n\nGetting started with MCPJungle is straightforward. You can quickly set up the server using Docker Compose or install the CLI tool directly.\n\nTo start the MCPJungle server locally with Docker Compose:\n\nbash\ncurl -O https://raw.githubusercontent.com/mcpjungle/MCPJungle/refs/heads/main/docker-compose.yaml\ndocker compose up -d\n\n\nFor managing MCPJungle from your local machine, install the CLI using Homebrew:\n\nbash\nbrew install mcpjungle/mcpjungle/mcpjungle\n\n\nYou can also pull the Docker image for the server:\n\nbash\ndocker pull ghcr.io/mcpjungle/mcpjungle\n\n\n## Examples\n\nMCPJungle simplifies the process of integrating and managing tools for your AI agents. Here are a few examples:\n\n**Registering an MCP Server:**\nYou can register a streamable HTTP-based MCP server, like `context7`, using the CLI:\n\nbash\nmcpjungle register --name context7 --url https://mcp.context7.com/mcp\n\n\n**Connecting AI Clients:**\nConfigure your AI clients, such as Claude or Cursor, to connect to MCPJungle. For Claude, you would add the following to your `mcpServers` configuration:\n\n\n{\n  \"mcpServers\": {\n    \"mcpjungle\": {\n      \"command\": \"npx\",\n      \"args\": [\n        \"mcp-remote\",\n        \"http://localhost:8080/mcp\",\n        \"--allow-http\"\n      ]\n    }\n  }\n}\n\n\nFor Cursor, the configuration is even simpler:\n\n\n{\n  \"mcpServers\": {\n    \"mcpjungle\": {\n      \"url\": \"http://localhost:8080/mcp\"\n    }\n  }\n}\n\n\nOnce connected, your AI agents can discover and utilize the tools registered in MCPJungle.\n\n**Tool Groups for Granular Control:**\nMCPJungle allows you to create Tool Groups, exposing only a specific subset of tools to your AI clients. This helps manage performance and provides granular access control. For example, to create a group with specific tools:\n\n\n{\n  \"name\": \"claude-tools\",\n  \"description\": \"This group only contains tools for Claude Desktop to use\",\n  \"included_tools\": [\n    \"filesystem__read_file\",\n    \"deepwiki__read_wiki_contents\",\n    \"time__get_current_time\"\n  ]\n}\n\n\nThen, create the group using the CLI:\n\nbash\nmcpjungle create group -c ./claude-tools-group.json\n\n\n## Why Use MCPJungle\n\nMCPJungle addresses critical needs for developers and organizations working with AI agents:\n\n*   **For Developers using MCP Clients**: It provides a central hub to access MCP servers for tool-calling, simplifying integration with clients like Claude and Cursor.\n*   **For Developers Building Production-Grade AI Agents**: It offers built-in security, privacy, and Access Control, essential for robust and reliable AI agent deployments.\n*   **For Organizations**: It enables centralized viewing and management of all MCP client-server interactions, hosted securely within their own datacenter, ensuring data governance and operational oversight.\n\n## Links\n\n*   **GitHub Repository**: [https://github.com/mcpjungle/MCPJungle](https://github.com/mcpjungle/MCPJungle){:target=\"_blank\"}\n*   **Model Context Protocol**: [https://modelcontextprotocol.io/introduction](https://modelcontextprotocol.io/introduction){:target=\"_blank\"}\n*   **Discord Community**: [https://discord.gg/CapV4Z3krk](https://discord.gg/CapV4Z3krk){:target=\"_blank\"}","metrics":{"detailViews":11,"githubClicks":9},"dates":{"published":null,"modified":"2026-01-30T16:01:07.000Z"}}