io.github.onepunchtechnology/glassypic

by onepunchtechnology · remote · local (npm) · no sign-in to list tools · v2.1.3 · published by GitHub user onepunchtechnology

Production-ready images in one pass: resize, crop, compress, convert format, upscale, tag for SEO

Changes · 2

Compare Registry entry

3 tools: 2 change things and 1 only read.

Scanned Oct 21, 2026

Deletes or cancels0Claude Code: deny
Can't be undone0Claude Code: ask
Changes things2Claude Code: ask: see these tools
Only reads1Claude Code: allow: see these tools

No check matched anything in the tool definitions. No finding is not a safety guarantee. How the checks work.

claude mcp add --transport http glassypic https://app.glassypic.com/mcp

Tools

Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.

3 tools

Changes things 2Creates or changes something that can be changed back.Claude Code: ask

optimize_imageOptimize an image: smart lossy compression (typically 60-80% size reduction), optional resize/upscale/format conversion, and AI-generated SEO metadata.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it
Optimize an image: smart lossy compression (typically 60-80% size reduction), optional resize/upscale/format conversion, and AI-generated SEO metadata. Accepts absolute local file paths or remote URLs. In remote/API mode, only remote URLs are supported. Supported input formats: JPG, PNG, WebP, AVIF, GIF, SVG, ICO, HEIC, TIFF, BMP (max 50 MB). Supported output formats: JPG, PNG, WebP, AVIF, GIF, SVG, ICO. Credits: 3 to compress (always), +1 if width or height is set, +2 to upscale, +1 for SEO tags (on by default). A full pipeline is 7 credits. Upscale is charged whether you request it or the server adds it automatically — it does so whenever a resize target exceeds the source by more than 1.2x, so a resize-only call on a small image also costs 7. SVG or ICO output is a flat 1 credit, overriding everything above. Animated GIFs are billed per frame: (per-frame operations x frames) + 1 if tags, up to 601 credits at the 100-frame limit — confirm_gif_cost gates that path. GIFs are excluded from automatic upscaling. Works as a guest with no signup. Log in with the login tool for more credits. Use status tool to check remaining credits before batch processing.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
upgradeOpen the GlassyPic pricing page in the user's browser, where the account's plan can be reviewed and changed.Reads text others writeNo findings
Why it is in this group
- The description's first verb is "open": a word for a change.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it
Open the GlassyPic pricing page in the user's browser, where the account's plan can be reviewed and changed. Call this only when the user asks to change or review their plan.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true

Only reads 1Looks things up and changes nothing.Claude Code: allow

statusCheck your GlassyPic account status: login state, tier, credits remaining, and credit reset time.Reads text others writeNo findings
Why it is in this group
- The name "status" says "status": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it
Check your GlassyPic account status: login state, tier, credits remaining, and credit reset time. Use this before batch processing to verify sufficient credits.
Annotations the server declares
- readOnlyHint: true
- idempotentHint: true
- openWorldHint: true

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or outbound.

Reads private data0: Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write3: Brings in text someone else can write: web pages, inbound email, messages, issues and comments.; optimize_image
status
upgrade
Can send data out0: Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Remote posture

What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.

Looked at Oct 22, 2026, 15:03 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable: yes
HTTP status of an anonymous initialize: 200
tools/list served without credentials: yes
Tools that change things, listed without credentials: 2
Protocol version: 2025-06-18
WWW-Authenticate on 401: not observed
resource_metadata in WWW-Authenticate: none
RFC 9728 protected resource metadata: none
Authorization servers: none
Legacy HTTP+SSE transport: no
Dynamic client registration: not observed
Client ID metadata documents: not observed

WarnThe whole server
The endpoint served tools/list without credentials, and the list has 2 tools that change things (2 write). Whether a call also works without credentials was not tested: tools are never called.
Matched text
https://app.glassypic.com/mcp: tools/list returned 3 tools to an anonymous client, including optimize_image (write), upgrade (write)
What this check looks for

Install

Pinned to version 2.1.3. Values in angle brackets are yours to fill in.

claude mcp add --transport http glassypic https://app.glassypic.com/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json

{
  "permissions": {
    "allow": [
      "mcp__glassypic__status"
    ],
    "ask": [
      "mcp__glassypic__optimize_image",
      "mcp__glassypic__upgrade"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as glassypic. Review it before you use it.

Capability tags behind 3 rules

mcp__glassypic__optimize_image untrusted-input
mcp__glassypic__status untrusted-input
mcp__glassypic__upgrade untrusted-input

Keep track

Get told when this server's tools change: a new tool, a new description, a new class.

https://anlyon.dev/servers/io.github.onepunchtechnology/glassypic/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Anlyon alternative

2 of these tools change something. Run those as governed actions.

Declare what an action changes, and Anlyon puts it under a shared limit, binds every approval to the exact request, and grades the outcome. It works on any HTTPS API you can describe as an action.

Anlyon does not run, proxy or govern this MCP server. A tool your own code calls directly is not routed through Anlyon and is not governed by it.

Import an OpenAPI spec →

Compare with other servers for the same product.

Source: MCP Registry · repository. Synced Oct 21, 2026, 18:42 UTC.

For agents: Markdown · JSON · report this listing