Textile Designer AI

Name: Textile Designer AI
Author: textile-designer.ai

Local

textile-designer.aiMedia & Design0Updated 3w ago

Repository Visit website

About Textile Designer AI

Textile Designer AI is an MCP server for running textile and print-design tools on local image files through Claude or other MCP clients. It covers print preparation, pattern repeats, colourways, separation, and additional design effects, with outputs saved beside the source image.

Key features

01Print-ready upscaling
02Seamless pattern repeats
03Colourway generation
04Screen separation to multichannel PSD
05Background and watermark removal
06Vectorization and design effects

Use cases

01Prepare an image for print
02Create a half-drop pattern repeat
03Generate colourways from artwork
04Separate artwork into print screens

MCP support

The MCP server exposes Textile Designer AI design tools to Claude and other MCP clients. It sends selected images and run settings to Textile Designer AI and returns resulting files.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config

{
  "mcpServers": {
    "ai-textile-designer": {
      "command": "npx",
      "args": [
        "-y",
        "@textile-designer-ai/mcp"
      ]
    }
  }
}

Run commandnpx -y @textile-designer-ai/mcp

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages

npm@textile-designer-ai/mcp0.1.2stdio

Tools

Saved tool list · updated 2w ago

Parameter	Type	Required	Description
open_browser	boolean	No	Open the verification URL in the default browser. Default true.
wait_seconds	integer	No	Block up to this many seconds for the link to complete. Default 0 (return at once).

Details

From the project README

Textile Designer AI for Claude

Run the Textile Designer AI design tools from Claude on the image files on your computer: print-ready upscaling, seamless repeats (block, half brick, half drop), Super Scaler, background and watermark removal, Dress to Design (extract the print from a garment photo), Colourways, Colour and Object Layering, Channeling (screen separation into a multichannel PSD), Vectorizer, 3D and Embroidery effects, Sketch to Design, Design Generation, Spec Board and more.

Results are saved as files next to your input image, and Claude shows you a preview, the file paths and the credits used.

What you need

A Textile Designer AI account with credits or a plan: sign up.
Node.js 18 or newer (the plugin starts the server with npx).

Install

Claude directory: search for Textile Designer AI and install it.

Claude Code, from this repository:

/plugin marketplace add ScientiaAI/textile-designer-ai-claude
/plugin install textile-designer-ai@textile-designer-ai

Any MCP client without the plugin (Claude Desktop config, Codex, Cursor, VS Code): run npx -y @textile-designer-ai/mcp. Setup snippets for each client are in the package README.

Using it

Ask Claude in plain words, for example:

"Connect to Textile Designer AI."
"Make a half-drop repeat of C:\designs\paisley.png at 300 dpi."
"What would Dress to Design cost on dress.jpg with 2 outputs?"
"Upscale floral.png 4x, then separate it into 8 screens."

When a tool has modes or settings you have not chosen, Claude asks you, one question at a time, with the recommended option preselected. Nothing is uploaded or charged until you answer, and prices are shown only when you ask.

Ask Claude things like "which tool should I use for a screen print?" or "how is Ready to Print different from Super Scaler?": it answers from the built-in Textile Designer AI guide.

What this plugin runs and sends

It runs the MIT-licensed MCP server @textile-designer-ai/mcp on your computer, pinned to an exact version.
It sends only the images you ask it to process, and the settings for that run, to https://www.textile-designer.ai, and downloads the results from Textile Designer AI's storage. It sends nothing else and runs nothing in the background.
Your login is a device-code sign-in in your browser. The session token is stored in ~/.textile-designer/mcp-session.json, readable only by you, and is never shown in chat.
It also reads the list of image files in the input image's folder, only to count them for an optional one-time Image Search tip.
It reads your account's email, organisation, credit balance and plan from Textile Designer AI only to show them to you and to apply your plan's rules. Nothing is shared with anyone else.
Images and results you process are kept in your Textile Designer AI account Library, as described in the privacy policy below. Run logout to remove the stored session.

Security

To report a security vulnerability in this plugin or the MCP server, write to us through https://www.textile-designer.ai/contact with "Security" in the subject. We acknowledge reports and fix confirmed issues in a new pinned release.

License

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

Read the getting-started guide

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.