Local Image Gen

MCP server for local image generation. Designed to run on a Windows GPU box (RTX 3060 12GB at your parents' house) and be called remotely by Claude Cowork on a MacBook over Tailscale.

• Backend: black-forest-labs/FLUX.2-klein-4B via Hugging Face diffusers

• Server: FastMCP over HTTP (streamable-http transport)

• Tool: generate_image (one tool, that's it for the MVP)

Setup on the Windows GPU host

Prereqs: Windows 10/11, NVIDIA RTX 3060 (12GB) with up-to-date driver, Python 3.11+ available.

git clone <this-repo>
cd Local-Image-Gen
.\scripts\setup_windows.ps1
.venv\Scripts\Activate.ps1
huggingface-cli login   # needed if the model is gated
copy .env.example .env
uv run main.py

The first call to generate_image will download the model to ./models/ (~10 GB, one-time). Watch for [pipeline] ready in the server output before invoking tools from Cowork.

Related MCP server: Flux Schnell Server

Adding to Claude Cowork (MacBook)

In Cowork's MCP config:

{
  "mcpServers": {
    "local-image-gen": {
      "url": "http://<windows-pc-tailscale-ip>:8765/mcp"
    }
  }
}

The Windows PC's Tailscale IP looks like 100.x.y.z — get it with tailscale ip -4 on the Windows box.

The generate_image tool

Returns:

{
  "image_b64": "<base64 PNG>",
  "path": "C:\\...\\generated\\1234567890_abc123.png",
  "seed_used": 1234567890,
  "width": 1024,
  "height": 1024,
  "elapsed_seconds": 3.42
}

On error:

{ "error": "CUDA out of memory...", "error_type": "OOM" }

Config (env vars, prefix IMG_)

Networking: MacBook ↔ Windows PC

Use Tailscale — free for personal use, no port forwarding on the parents' router, encrypted.

1. Install Tailscale on both machines, sign in to the same account

2. Note the Windows PC's Tailscale IP (100.x.y.z)

3. Use that IP in the Cowork MCP config above

For wake-on-LAN (so the PC doesn't have to run 24/7):

• Enable "Wake on LAN" in BIOS and in the NIC's advanced power settings

• Tailscale's tailscale wake <hostname> from the Mac will turn it on

Dev on the MacBook (no GPU)

You can iterate on the server code without a GPU by switching to a small model:

IMG_MODEL_ID=stable-diffusion-v1-5/stable-diffusion-v1-5 IMG_DEVICE=cpu uv run main.py

CPU generation is slow (~minutes per image) but the round-trip works.