Glassypic logo

Glassypic

Process images through GlassyPic for compression, resizing, format conversion, upscaling, and SEO metadata.

Install Glassypic

Pick your client, then add it in one click or paste the config.

STDIONode.js
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "glassypic": {
      "command": "npx",
      "args": [
        "-y",
        "@glassypic/mcp-server@latest"
      ]
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

Automated check passed— started and listed 5 tools correctly (14d ago).

Overview

The glassypic MCP server connects an MCP client to GlassyPic for image optimization through one natural-language-oriented tool. It can compress, resize, crop, upscale, convert formats, and generate SEO filenames and alt text from local files or URLs. Use it when an agent needs to prepare image assets without adding separate image-processing utilities. The server runs over stdio through an npx package and provides 20 free daily credits without signup.

Use cases

  • Compress images for web delivery
  • Convert source assets to WebP or AVIF
  • Resize images to fixed dimensions with padding or cropping
  • Upscale small graphics by 2× or 4×
  • Generate SEO filenames and alt text

Key features

  • Image compression
  • Proportional and exact resizing
  • Smart cropping and white padding
  • 2× and 4× AI upscaling
  • Format conversion across raster and vector formats
  • SEO filename, alt text, and keyword generation

Tools5

What Glassypic lets your agent do. Expand a tool for its parameters.

Verified live~1.5k tokens of context

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked 2d ago

Recent health check succeeded.

7/7 checks healthy over the last 45d

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 12d ago via OSV.dev · @glassypic/mcp-server@latest (npm)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

GitHub stars2Stargazers on the source repository.
npm downloads408Package downloads in the last 30 days.
Last commit6d agoMost recent push to the default branch.
Availability100%Our rolling endpoint + install checks that succeeded.
Install checkPassedOur sandbox started it and listed its tools.
Tools exposed5Callable tools this server registers over MCP.
Directory activity3 viewsConfig copies, upvotes, and views on AllMCPs.

How Glassypic works

What glassypic MCP server does

The glassypic MCP server exposes GlassyPic's image optimization workflow to MCP clients through a single tool named optimize_image. It accepts an absolute local path or a remote URL and produces an optimized asset at a selected path or directory. If no destination is supplied, the result is saved beside the source image with either an SEO-based filename or a .polished suffix.

The tool can compress an image while retaining its format and dimensions, change the output format, resize proportionally, or produce exact dimensions. When both width and height are supplied, the default behavior adds white padding; selecting crop uses a smart crop instead. AI upscaling is available at 2× or 4×. SEO generation is enabled by default and can return an alt text, keyword list, and slug-based filename.

How it works

The glassypic MCP server receives tool arguments from the connected client, sends the image through GlassyPic's server-side processing pipeline, and returns both a text summary and structured output. Results include the output path, byte size, dimensions, format, compression ratio, and any generated SEO fields. The service typically applies additional compression as part of processing; a requested maximum file size is a target rather than a guarantee.

Supported input formats include JPG, PNG, WebP, AVIF, GIF, SVG, ICO, HEIC, HEIF, TIFF, and BMP. Output formats are JPG, PNG, WebP, AVIF, GIF, SVG, and ICO. HEIC, TIFF, and BMP inputs are converted to JPG during upload because they are not available as output formats. SVG files can remain vector files or be converted to and from raster formats, while ICO processing can create a favicon set or a specified single size.

Animated GIFs require special handling. GIF output preserves animation and can use a frame limit from 1 to 100 to reduce processing cost. Converting an animated GIF to JPG, PNG, WebP, or AVIF keeps only its first frame. The client must set confirm_gif_cost to true after the animated-image cost warning before processing proceeds. Uploads are limited to 50 MB.

Setup and configuration

Install the glassypic MCP server by adding its stdio command to an MCP client configuration:

config.json
{
  "mcpServers": {
    "glassypic": {
      "command": "npx",
      "args": ["-y", "@glassypic/mcp-server@latest"]
    }
  }
}

The package does not require signup and includes 20 free daily credits. Claude Desktop, Cursor, Windsurf, and Cline use JSON configuration files. Claude Code, Gemini CLI, and OpenAI Codex CLI also provide commands for registering the server. On Windows, clients that cannot resolve npx from PATH may need to invoke it through cmd /c; this workaround does not apply to the listed CLI registration commands.

Tools and capabilities

The optimize_image tool supports these main options:

  • input: an absolute local path or remote URL.
  • output_path: a file path or directory for the result.
  • output_format: jpg, png, webp, avif, gif, svg, ico, or original.
  • output_width_px and output_height_px: proportional or exact resizing controls.
  • output_resize_behavior: pad or crop when both dimensions are provided.
  • output_upscale_factor: 2× or 4× AI upscaling.
  • output_seo_tag_gen: enables or disables SEO metadata generation.
  • output_file_size_limit: a target maximum size in bytes.
  • gif_frame_limit and confirm_gif_cost: controls for animated GIF processing.

The glassypic MCP server is a fit for preparing web images, converting asset formats, generating favicons, resizing graphics for fixed layouts, and producing SEO metadata alongside processed files.

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about Glassypic

glassypic is an MCP server that connects AI clients to GlassyPic for image processing. Its main tool, optimize_image, compresses, resizes, crops, upscales, and converts images, while also generating SEO filenames, alt text, and keywords. It accepts local file paths or remote URLs and returns the processed asset details.

Install it by adding an stdio entry that runs `npx -y @glassypic/mcp-server@latest` to your MCP client configuration. The README provides setup examples for Claude Desktop, Cursor, Windsurf, Cline, Claude Code, Gemini CLI, and OpenAI Codex CLI.

Yes, glassypic works with Cursor by adding the server entry to `.cursor/mcp.json` in the project root. Use `npx` as the command and `-y @glassypic/mcp-server@latest` as its arguments.

Yes, glassypic can output WebP or AVIF through the `output_format` parameter. It supports conversion from the documented input formats, including JPG, PNG, GIF, SVG, ICO, HEIC, TIFF, and BMP, subject to the server's format behavior.

Animated GIFs remain animated when the output format is GIF, and processing can use a frame limit from 1 to 100. Conversion to JPG, PNG, WebP, or AVIF keeps only the first frame. Set `confirm_gif_cost` to `true` after the cost warning to continue.

Related MCP servers

Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewGlassypic AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/glassypic?style=directory)](https://allmcps.com/mcp/glassypic)
HTML Embed
<a href="https://allmcps.com/mcp/glassypic"><img src="https://allmcps.com/api/badge/glassypic?style=directory" alt="Glassypic on AllMCPs" /></a>