EN | 中文

🖥️ MTCode Server

Publish any local TCP service through MTCode DirectLink — SSH, web apps, remote desktop, Ollama, vLLM, LM Studio, OpenClaw, or your own custom server. Built-in MTCode-LLM and MTCode-Diffusion servers are included for a fast start with local AI.

🛡 Privacy — End-to-end encrypted. No MTCode infrastructure in your data path.
⚡ Simplicity — No public IP, domain, VPN, or port forwarding.
🚀 Performance — Direct peer-to-peer data path. No relay hop.

What Is MTCode Server?

MTCode Server runs on the computer that hosts your services. It registers selected local TCP ports with MTCode DirectLink and makes them accessible to authorized users through MTCode Portal — without exposing the whole computer or opening public ports.

It works with any TCP-based service, including HTTP, HTTPS, WebSocket, gRPC, SSH, SFTP, RDP, VNC, Ollama, LM Studio, vLLM, OpenClaw, and custom applications.

For a quick start with local AI, MTCode Server also includes:

How It Works

MTCode Server authenticates with the platform using your administrator account and registers the local services you choose to share.

Registered services appear automatically in each authorized user’s MTCode Portal. When a user connects, MTCode Server establishes a direct peer-to-peer data channel with that user’s MTCode Portal.

Application traffic flows directly between the two endpoints and is end-to-end encrypted, without passing through an intermediate relay.

Only the services you register are exposed to authorized users. The rest of the computer remains inaccessible.

MTCode Server Live Demo Videos

On a desktop computer with a RTX 4090 24 GB GPU, MTCode Server registers three servers: SSH Server, MTCode-LLM, MTCode-Diffusion

Register SSH Server

Register LLM Server

Register Diffusion Server

Getting Started

If you only plan to use third-party services, the CPU-only package is sufficient and much smaller.

Three Ways to Serve

MTCode Server supports three usage modes, listed in typical order of adoption:

🔌

External Mode — Publish an Existing Service

Your service is already running; you simply register its port.

  • Works with any TCP service (SSH, web, remote desktop, AI servers, etc.)
  • No changes to how your service runs
  • Just specify the port and (optionally) the protocol
🛠️

Managed Mode — Let MTCode Server Run It

MTCode Server launches and manages the service process for you.

  • Start/stop both the service and its sharing from one place
  • View logs directly in the interface
  • Supports auto-start on reboot
🦙

Built-In AI Servers — Quick Start

If you don’t already run local AI services, MTCode Server includes:

  • MTCode-LLM — chat, coding, multimodal analysis
  • MTCode-Diffusion — image generation and editing

Both include:

  • Curated model selection with quantization options
  • One-click download from Hugging Face
  • Built-in web interfaces for immediate use

External Mode — Examples

SSH server

On MTCode Server:
  • Enter a descriptive name (e.g., "My SSH Server: Office")
  • Set the port to 22 and select protocol SSH
  • Click Start

Remote users connect via MTCode Portal, which maps the service to a local port and launches:

ssh -p <port> localhost

Ollama server

Run ollama serve.
On MTCode Server:
  • Enter a descriptive name (e.g., “My Ollama Server: Home”)"
  • Set the port to 11434 and select protocol HTTP
  • Click Start

On remote users' computers, MTCode Portal maps the Ollama server to a local port. Double-click the port number to change it to 11434 if needed.
Users can then connect to Ollama using any Ollama-compatible tool, just as if it were running locally.

Protocol Selection

The optional protocol setting enables:

  • Smart encryption handling: If the protocol already provides encryption (e.g., HTTPS, SSH), MTCode avoids double encryption.
  • Protocol-aware connect actions: MTCode Portal launches the appropriate tool — opening a browser for HTTP/HTTPS, launching a terminal for SSH/SFTP, starting Remote Desktop for RDP, and so on.
MTCode Server configured to forward local SSH server on port 22 with encryption disabled

MTCode Server registering a local SSH server on port 22 — channel encryption is disabled since SSH provides its own end-to-end encryption

Managed Mode — Let MTCode Server Run the Process for You

Instead of starting your service in a separate terminal, let MTCode Server launch and manage it for you. This simplifies day-to-day operation and makes auto-start straightforward: when MTCode Server starts at login or boot, your service starts automatically with it.

What you get

  • A single Start / Stop control for both the service and its publication
  • Server stdout/stderr captured in the Server Log tab
  • Seamless integration with Auto-Start, so the service restarts after reboot or login

Example — Launch Ollama with MTCode Server

In the Server Command Line field, enter:
ollama serve
Then:
  • Enter a descriptive name (e.g., “My Ollama Server: Home”)"
  • Set the port to 11434 and select protocol HTTP
  • Click Start

Remote users connect to the service in exactly the same way, regardless of how the underlying process is started.

Built-In AI Servers

If you don't already run a local AI server, MTCode Server includes two of them, MTCode-LLM and MTCode-Diffusion. You could start an AI server right away.

🦙 MTCode-LLM Server

  • Based on llama.cpp
  • Supports chat, coding, and multimodal tasks
  • OpenAI- and Ollama-compatible API
  • Built-in web UI for file attachment and Q & A

🎨 MTCode-Diffusion Server

  • Based on stable-diffusion.cpp
  • Supports SD 1.x/2.x, SDXL, SD3, Flux, Qwen
  • Includes ControlNet, LoRA, ESRGAN
  • Built-in web UI for text-to-image generation and image editing

MTCode LLM Server web interface for attaching files, questions and answers

MTCode-LLM — web UI for attaching files, questions and answers

MTCode Diffusion Server web interface for image generation

MTCode-Diffusion — web UI for text-to-image generation and image editing

Automatic Startup

Configure MTCode Server to start automatically so your AI server is always available — even after a computer restart.

🔄

Auto Login + Auto Start

Configures the operating system to log in automatically at boot, then launches MTCode Server and starts the AI server — no user interaction needed. Ideal for dedicated server machines that should resume service after a power outage or reboot. Requires administrator privileges to set up.

👤

Auto Start at User Login

MTCode Server launches automatically after you log in to your computer and starts the AI server immediately. No administrator privileges required — just log in and your server is ready.

⏸️

No Auto-Start

Launch MTCode Server manually when you need it. Full control over when the server runs.

System Requirements

Minimum

Operating SystemWindows 10+, macOS 11+, or Linux (e.g. Ubuntu 20.04+, Fedora, Arch)
CPU64-bit processor
RAM8 GB
GPUOptional (for third-party servers that do not require a GPU)

Recommended for AI Servers

GPUGPU with 8 GB+ VRAM
VRAM for LLMs8 GB for 6B models with 4096 context size, 16 GB for 10B models with 8192 context size, 24 GB for 14B models with 16384 ~ 32768 context size
VRAM for Image Gen8 GB for SD 1.x/2.x, 12 GB for SDXL/SD3, 16 GB+ for Flux, 24 GB+ for Qwen
× ×