Provides deployment options for running MCPX through containerization, with official Docker images available for easy setup.
Offers version tracking and releases through GitHub, with the server codebase hosted and maintained there.
Features demonstration content hosted on YouTube, accessible via an embedded demo video showing MCPX functionality.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@MCPX MCP Gateway list all connected MCP servers"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Lunar MCPX is an MCP server which serves as an aggregator for other MCP servers. Its primary goal is to simplify the integration and management of multiple MCP servers dynamically. By using MCPX, developers can easily manage connections to various MCP-compatible services through simple configuration changes, enabling rapid integration with no coding involved.
MCPX provides:
Dynamic MCP servers dispatch
Zero-code integration with MCP services via JSON configuration
Unified API interface to multiple MCP services
A remote-first approach
Related MCP server: MCPHub
This repository helps you get up and running quickly. For detailed feature guides, architecture, and advanced options, head to the official docs.
You can run Lunar MCPX locally or via Docker.
Before you start: it's assumed you already have an MCP-compatible client. If not, Claude Desktop is a good place to start.
Run with Docker:
Use the Official Docker Image Guide
The Control Plane helps you inspect live traffic and manage your MCPX instance. Setup instructions are available here.
Once MCPX is running, you can connect a client using one of the following methods:
This server cannot be deployed
The Remote MCP server acts as a standardized bridge between LLM applications (like Claude, ChatGPT, and Cursor) and external services, enabling AI agents to access external tools and resources. Its primary capability is providing a centralized search tool to discover other MCP servers and their respective tools. Unlike local implementations, it runs remotely with OAuth authentication and permission controls for security.
Zero-setup MCP gateway securely connecting AI to your tools with authentication and workflows
One MCP endpoint for Claude, GPT & Gemini: 100+ tools + no-code connectors + agent workers.
MCP server connecting AI agents to 100+ apps (Gmail, Slack, Notion, GitHub) via one-click OAuth.
