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., "@mcp-image-previewer preview the base64 image"
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.
An MCP (Model Context Protocol) server that previews base64-encoded images in a native GUI window using Slint.
Native GUI — Slint-based window, no Python or external runtime needed
Window reuse — Same window updates in-place across multiple images
Always-on-top — Optionally pin the preview window above other windows
Show/hide — Toggle window visibility without losing state
Format support — PNG, JPEG, WebP, GIF, TIFF, etc. (via sharp)
Related MCP server: image-to-base64
Node.js 18+
claude mcp add image-previewer -- npx mcp-image-previewerAdd to your MCP client configuration:
{
"mcpServers": {
"image-previewer": {
"command": "npx",
"args": ["mcp-image-previewer"]
}
}
}preview_imageDisplay a base64-encoded image in the viewer window.
Parameter | Type | Required | Description |
| string | Yes | Base64-encoded image data |
| string | Yes | MIME type (e.g. |
show_windowShow or hide the preview window.
Parameter | Type | Required | Description |
| boolean | Yes |
|
stay_on_topSet whether the preview window stays on top of other windows (X11/Windows only).
Parameter | Type | Required | Description |
| boolean | Yes |
|
npm install
npm run build
npm startMIT
This server cannot be deployed
Generate, render, and host Slidev presentations from markdown
Image and PDF toolkit: convert to AVIF/WebP/JXL, resize, crop, remove backgrounds, optimize PDFs.
Create, validate, edit, export (markdown/svg/png/mermaid), and search JSON Canvas files.
AI image + video generation for agents: --flag prompt DSL, async generate/poll, x402 pay-per-use.
