MCPJungle
MCPJungle is a self-hosted MCP Registry and Gateway suitable for both local and enterprise deployments. It provides a single URL for your MCP clients to access servers and a central platform for you to track your MCPs and client-server interactions.
What is MCPJungle?
MCPJungle is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to mcpjungle is a self-hosted mcp registry and gateway suitable for both local and enterprise deployments. it provides a single url for your mcp clients to access servers and a central platform for you t...
MCPJungle is a self-hosted MCP Registry and Gateway suitable for both local and enterprise deployments. It provides a single URL for your MCP clients to access servers and a central platform for you to track your MCPs and client-server interactions.
This server falls under the Cloud Services category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- MCPJungle is a self-hosted MCP Registry and Gateway suitable
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx mcpjungle-mcp-gatewayConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use MCPJungle
MCPJungle is a self-hosted MCP Registry and Gateway written in Go that aggregates multiple MCP servers behind a single unified endpoint, allowing AI clients to discover and invoke tools from any registered server without individual configurations. It supports both Streamable HTTP and STDIO transport types, offers enterprise features including bearer token authentication, OpenTelemetry observability, tool groups for selective exposure, and stateful or stateless session modes. DevOps teams and AI platform engineers deploy MCPJungle to centralize MCP infrastructure, track all client-server interactions, and manage the MCP lifecycle across their organization.
Prerequisites
- Docker and Docker Compose (for the server component), or a Go 1.21+ environment to build from source
- The mcpjungle CLI (via Homebrew on macOS or downloaded from GitHub Releases)
- An MCP client such as Claude Desktop (requires mcp-remote for HTTP transport)
- Node.js with npx (for mcp-remote if your MCP client only supports stdio)
Install the MCPJungle CLI
Install the mcpjungle CLI using Homebrew on macOS, or download a binary from the GitHub Releases page for Linux/Windows.
# macOS
brew install mcpjungle/mcpjungle/mcpjungle
# Verify
mcpjungle versionStart the MCPJungle server with Docker Compose
Download the Docker Compose file and start the gateway server. It runs on port 8080 by default and uses SQLite for storage unless DATABASE_URL is set for PostgreSQL.
curl -O https://raw.githubusercontent.com/mcpjungle/MCPJungle/refs/heads/main/docker-compose.yaml
docker compose up -dRegister MCP servers with the gateway
Use the CLI to register existing MCP servers. Streamable HTTP servers are registered by URL; STDIO servers by command and args.
# Register a remote HTTP MCP server
mcpjungle register --name context7 --url https://mcp.context7.com/mcp
# Register a local STDIO MCP server
mcpjungle register --name filesystem \
--transport stdio \
--command npx \
--args "-y @modelcontextprotocol/server-filesystem ." Configure your MCP client to connect to MCPJungle
Point your MCP client to the single MCPJungle gateway endpoint. Claude Desktop needs mcp-remote since it doesn't natively support HTTP transport.
{
"mcpServers": {
"mcpjungle": {
"command": "npx",
"args": ["mcp-remote", "http://localhost:8080/mcp", "--allow-http"]
}
}
}List registered servers and invoke a tool
Use the CLI to verify registered servers, then invoke a tool using the canonical naming format server-name__tool-name.
# List registered servers
mcpjungle list
# Invoke a tool directly via CLI
mcpjungle invoke filesystem__list_directory --input '{"path": "."}' MCPJungle Examples
Client configuration
Claude Desktop configuration connecting to a local MCPJungle gateway via mcp-remote.
{
"mcpServers": {
"mcpjungle": {
"command": "npx",
"args": ["mcp-remote", "http://localhost:8080/mcp", "--allow-http"]
}
}
}Prompts to try
Example prompts once MCPJungle aggregates your MCP servers — Claude can access all registered tools through a single connection.
- "List all available tools across my registered MCP servers"
- "Search the Context7 documentation for React hooks usage"
- "List the files in my current project directory using the filesystem server"
- "What MCP servers are currently registered in MCPJungle?"
- "Use the Brave Search server to find recent news about DaVinci Resolve updates"Troubleshooting MCPJungle
mcp-remote cannot connect to localhost:8080
Verify the MCPJungle server is running with 'docker compose ps' or 'mcpjungle server status'. The --allow-http flag is required when connecting to non-HTTPS localhost endpoints. Check that port 8080 is not blocked by a firewall.
Registered STDIO servers fail to start through the gateway
Ensure the command and args in your registration are exactly as they would be run locally. Test the STDIO command directly in a terminal first. Environment variables for STDIO servers can be passed during registration using the --env flag.
Tools from registered servers do not appear in the AI client
Run 'mcpjungle list' to confirm servers are registered and active. Then restart your MCP client to force a fresh tool discovery. If a server is disabled, re-enable it with 'mcpjungle enable --name <server-name>'.
Frequently Asked Questions about MCPJungle
What is MCPJungle?
MCPJungle is a Model Context Protocol (MCP) server that mcpjungle is a self-hosted mcp registry and gateway suitable for both local and enterprise deployments. it provides a single url for your mcp clients to access servers and a central platform for you to track your mcps and client-server interactions. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install MCPJungle?
Follow the installation instructions on the MCPJungle GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with MCPJungle?
MCPJungle works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is MCPJungle free to use?
Yes, MCPJungle is open source and available under the MPL-2.0 license. You can use it freely in both personal and commercial projects.
MCPJungle Alternatives — Similar Cloud Services Servers
Looking for alternatives to MCPJungle? Here are other popular cloud services servers you can use with Claude, Cursor, and VS Code.
Open WebUI
★ 138.2kUser-friendly AI Interface (Supports Ollama, OpenAI API, ...)
Anything LLM
★ 60.4kThe all-in-one AI productivity accelerator. On device and privacy first with no annoying setup or configuration.
LocalAI
★ 46.4kLocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.
Nacos
★ 33.0kan easy-to-use dynamic service discovery, configuration and service management platform for building AI cloud native applications.
Xiaozhi ESP32
★ 26.7k本项目为xiaozhi-esp32提供后端服务，帮助您快速搭建ESP32设备控制服务器。Backend service for xiaozhi-esp32, helps you quickly build an ESP32 device control server.
Gateway
★ 11.8kA blazing fast AI Gateway with integrated guardrails. Route to 1,600+ LLMs, 50+ AI Guardrails with 1 fast & friendly API.
Browse More Cloud Services MCP Servers
Explore all cloud services servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up MCPJungle in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use MCPJungle?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.