MCPJungle Server
One place to manage & connect to all your MCP servers
What is MCPJungle Server?
MCPJungle Server is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to one place to manage & connect to all your mcp servers
One place to manage & connect to all your MCP servers
This server falls under the Cloud Services category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- One place to manage & connect to all your MCP servers
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx mcpjungleConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use MCPJungle Server
MCPJungle Server is a self-hosted Go-based MCP Registry and Gateway that serves as a single management hub for all your MCP servers, exposing their combined tools through one unified endpoint to any AI client. By registering both remote HTTP and local STDIO MCP servers with MCPJungle, teams eliminate the need to configure each server individually in every AI tool, instead connecting once to the gateway and getting access to all registered capabilities. It includes enterprise-grade features like bearer token authentication, OpenTelemetry metrics, tool groups, and interaction logging for full observability over how AI agents use your MCP infrastructure.
Prerequisites
- Docker and Docker Compose for running the server, or Go 1.21+ to build from source
- The mcpjungle CLI installed (Homebrew on macOS or binary from GitHub Releases)
- Node.js with npx for mcp-remote (required for Claude Desktop stdio-to-HTTP bridging)
- An MCP client such as Claude Desktop, Claude Code, or Cursor
Install the MCPJungle CLI
Install the CLI tool that manages server registrations and communicates with the running gateway.
# macOS via Homebrew
brew install mcpjungle/mcpjungle/mcpjungle
# Verify
mcpjungle versionStart the MCPJungle gateway server
Pull the Docker Compose file and start the gateway. The server persists registrations in SQLite by default, or PostgreSQL if DATABASE_URL is configured.
curl -O https://raw.githubusercontent.com/mcpjungle/MCPJungle/refs/heads/main/docker-compose.yaml
docker compose up -d
# Check it's running
curl http://localhost:8080/healthRegister your existing MCP servers
Use the CLI to register any MCP server — either a remote HTTP endpoint or a local STDIO-based server. Both types become accessible through the single gateway.
# Remote HTTP MCP server
mcpjungle register --name brave-search \
--url https://your-brave-mcp-endpoint.com/mcp \
--bearer-token YOUR_TOKEN
# Local STDIO MCP server
mcpjungle register --name filesystem \
--transport stdio \
--command npx \
--args "-y @modelcontextprotocol/server-filesystem /home/user"Connect your MCP client to the gateway
Configure your AI client to point to the MCPJungle gateway. All tools from all registered servers are now available through this single connection.
{
"mcpServers": {
"mcpjungle": {
"command": "npx",
"args": ["mcp-remote", "http://localhost:8080/mcp", "--allow-http"]
}
}
}Manage servers and tool groups
Use the CLI to list registered servers, enable or disable individual servers, and create tool groups to selectively expose subsets of tools to different clients.
# List all registered servers
mcpjungle list
# Disable a server temporarily
mcpjungle disable --name filesystem
# Re-enable it
mcpjungle enable --name filesystemMCPJungle Server Examples
Client configuration
claude_desktop_config.json configuration for connecting to MCPJungle gateway using mcp-remote.
{
"mcpServers": {
"mcpjungle": {
"command": "npx",
"args": ["mcp-remote", "http://localhost:8080/mcp", "--allow-http"]
}
}
}Prompts to try
Example prompts after connecting multiple MCP servers through MCPJungle — Claude accesses all of them through a single gateway.
- "What tools are available from all my registered MCP servers?"
- "List files in my home directory using the filesystem server"
- "Search for documentation on Python async/await through the Context7 server"
- "Show me all MCP servers registered in MCPJungle and their status"
- "Use the Brave Search server to find the latest news about AI agent frameworks"Troubleshooting MCPJungle Server
Gateway returns 'connection refused' on port 8080
Check that the Docker containers are running with 'docker compose ps'. If the mcpjungle container exited, check logs with 'docker compose logs mcpjungle'. Ensure port 8080 is not already in use by another process.
Registered server tools are missing or not discovered
Verify the server is active with 'mcpjungle list'. For STDIO servers, test the command directly in your terminal to confirm it runs without errors. Restart your MCP client after registering new servers to trigger fresh tool discovery.
Bearer token authentication fails for registered servers
Ensure the --bearer-token value you provided during registration exactly matches the token expected by the upstream MCP server. You can update a server's configuration by deregistering and re-registering with the correct credentials.
Frequently Asked Questions about MCPJungle Server
What is MCPJungle Server?
MCPJungle Server is a Model Context Protocol (MCP) server that one place to manage & connect to all your mcp servers It connects AI assistants to external tools and data sources through a standardized interface.
How do I install MCPJungle Server?
Follow the installation instructions on the MCPJungle Server GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with MCPJungle Server?
MCPJungle Server works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is MCPJungle Server free to use?
Yes, MCPJungle Server is open source and available under the MPL-2.0 license. You can use it freely in both personal and commercial projects.
MCPJungle Server Alternatives — Similar Cloud Services Servers
Looking for alternatives to MCPJungle Server? 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 Server 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 Server?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.