Skip to content

ScreenshotMCP

by AgentForge-Labs · remote · no sign-in to list tools · v0.3.0 · published by GitHub user AgentForge-Labs

Desktop and mobile website screenshots plus page context for AI agents and automation workflows.

Final · 1

2 tools: 1 do something that can't be undone and 1 only read.

Scanned Oct 21, 2026

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

claude mcp add --transport http site-screenshot https://snapforge.web-tasarimci.com/mcp

Findings

Matches of fixed checks, with the text they matched.

1 warn
  • The server marks "capture_website" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".

    Matched text

    annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The name "capture_website" says "capture": a word that usually means money moves, which cannot be taken back.

    What this check looks for

Tools

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

2 tools

Can't be undone 1Claude Code: ask
  • capture_websiteCapture desktop, mobile, or both screenshots for a website.Reads text others writeCan send data out1 finding

    Why it is in this group

    • The name "capture_website" says "capture": a word that usually means money moves, which cannot be taken back.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.

    Findings

    • Warn

      The server marks "capture_website" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".

      Matched text

      annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The name "capture_website" says "capture": a word that usually means money moves, which cannot be taken back.

      What this check looks for
    Description, as the server wrote it
    Capture desktop, mobile, or both screenshots for a website. Successful screenshots are reused from cache until TTL expiry; failed or blocked captures are never cached and are retried live on the next call.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
Only reads 1Claude Code: allow, ask for 1 outbound
  • read_page_contextRender a public web page and return a compact Community agent-readable representation: visible text, clean Markdown, headings, links, forms, basic image metadata and interactive el…Reads text others writeCan send data outNo findings

    Why it is in this group

    • The name "read_page_context" says "read": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • untrusted-inputThe description's first sentence says "web": it reads web pages, which anyone can write.
    • untrusted-inputThe input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
    • outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.

    Claude Code: ask, because it is tagged outbound.

    Description, as the server wrote it
    Render a public web page and return a compact Community agent-readable representation: visible text, clean Markdown, headings, links, forms, basic image metadata and interactive elements with bounding boxes. No OCR, visual inference, crawl, sessions or advanced action selectors.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • 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.

Reads private data0
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write2
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out2
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, 14:50 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
1
Protocol version
2025-11-25
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
none
RFC 9728 protected resource metadata
https://snapforge.web-tasarimci.com/.well-known/oauth-protected-resource/mcp
Authorization servers
https://snapforge.web-tasarimci.com
Legacy HTTP+SSE transport
no
Dynamic client registration
yes
Client ID metadata documents
no
  • HighThe whole server

    The endpoint served tools/list without credentials, and the list has 1 tool that changes things (1 irreversible). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://snapforge.web-tasarimci.com/mcp: tools/list returned 2 tools to an anonymous client, including capture_website (irreversible)

    What this check looks for

Install

Pinned to version 0.3.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http site-screenshot https://snapforge.web-tasarimci.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": [],
    "ask": [
      "mcp__site-screenshot__capture_website",
      "mcp__site-screenshot__read_page_context"
    ],
    "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 site-screenshot. Review it before you use it.

Capability tags behind 2 rules
  • mcp__site-screenshot__capture_website untrusted-input, outbound
  • mcp__site-screenshot__read_page_context untrusted-input, outbound