Skip to content

Argoshot MCP server

io.github.rrlabs-io/argoshotrrlabs-iostreamable-httpv1.0.0Scanned

Give your agent eyes: screenshots of any web page it can see, pages as markdown, and PDFs.

6 tools: 3 change things and 3 only read.

Tools: 0 delete, 0 irreversible, 3 write, 3 read.
  • Reads private data · 1
  • Reads text others write · 4
  • Can send data out · 3
  • No findings

Tools listed without sign-in. Remote posture

With Anlyon

3 tools here change things. Govern them.

  • Anlyon lists the tools and adopts none.
  • Each tool you adopt gets approvals and receipts.
  • Your agent never holds the key.
Govern this server →

A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.

What the Argoshot MCP server can do

The Argoshot MCP server is published by the GitHub account rrlabs-io. It has 6 tools. It can create or change data (3 tools: render_html, page_to_markdown and page_to_pdf), but cannot delete data. 3 tools only read.

1 tool reads private data (screenshot_url); 4 tools bring in text other people can write (screenshot_url, render_html, page_to_markdown and 1 more); 3 tools can send data out of your system (screenshot_url, page_to_markdown and page_to_pdf). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way out.

None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.

Its remote endpoint lists its tools without sign-in.

Last scanned Nov 18, 2026, version 1.0.0.

Tools

Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.

6 tools

Changes things 3Claude Code: ask
  • page_to_markdownLoads a public page in a real browser (scripts run) and returns its content as Markdown.Reads text others writeCan send data outNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • 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.
    Description, as the server wrote it
    Loads a public page in a real browser (scripts run) and returns its content as Markdown. The text is cut at max_chars; the result says where to continue (offset). Each call counts as one render against the account's plan.

    Annotations the server declares

    • title: Read a web page as Markdown
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • page_to_pdfRenders a public page to a PDF and returns a link to the file (kept about 4 hours; PDFs are not shown inline).Reads text others writeCan send data outNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • 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.
    Description, as the server wrote it
    Renders a public page to a PDF and returns a link to the file (kept about 4 hours; PDFs are not shown inline). Each render counts against the account's plan.

    Annotations the server declares

    • title: Save a web page as PDF
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • render_htmlRenders an HTML and CSS string (an Open Graph card, an invoice, a template) to an image or PDF in a real browser.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.
    • 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.
    Description, as the server wrote it
    Renders an HTML and CSS string (an Open Graph card, an invoice, a template) to an image or PDF in a real browser. Resources the HTML loads from the web are fetched. Each render counts against the account's plan.

    Annotations the server declares

    • title: Render HTML to an image or PDF
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
Only reads 3Show 3 read-only tools
  • get_usageReturns the account's plan allowance: renders in total, available and used, the concurrency and per-minute limits, and when the period ends.No findings

    Why it is in this group

    • The name "get_usage" says "get": a word for reading.
    Description, as the server wrote it
    Returns the account's plan allowance: renders in total, available and used, the concurrency and per-minute limits, and when the period ends. Renders nothing and uses no credits.

    Annotations the server declares

    • title: Check screenshot usage
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • list_devicesLists the device presets (phones, tablets, desktops) with their viewport size and pixel ratio, optionally filtered by a part of the name.No findings

    Why it is in this group

    • The name "list_devices" says "list": a word for reading.
    Description, as the server wrote it
    Lists the device presets (phones, tablets, desktops) with their viewport size and pixel ratio, optionally filtered by a part of the name. Renders nothing and uses no credits.

    Annotations the server declares

    • title: List device presets
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • screenshot_urlRenders a public web page in a real browser and returns a screenshot: a preview image you can look at, plus a link to the stored file (kept about 4 hours).Reads private dataReads text others writeCan send data outNo findings

    Why it is in this group

    • The name "screenshot_url" says "screenshot": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "file": it reads files.
    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • untrusted-inputThe name "screenshot_url" says "screenshot" and "url": it reads web pages, which anyone can write.
    • 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
    Renders a public web page in a real browser and returns a screenshot: a preview image you can look at, plus a link to the stored file (kept about 4 hours). Supports device presets, full-page capture, a CSS selector, dark mode, and blocking ads and cookie banners. Fails for private or internal addresses. Each render counts against the account's plan.

    Annotations the server declares

    • title: Screenshot a web page
    • 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.

12 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 1 private-data tool breaks every one.

Reads private data1
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write4
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out3
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
deny to break every path
{
  "permissions": {
    "deny": [
      "mcp__argoshot__screenshot_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.

Tools listed without sign-in

Looked at Nov 18, 2026, 16:20 UTC, unchanged since Nov 18, 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
3
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
not observed
Authorization servers
not observed
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 3 tools that change things (3 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://api.argoshot.com/mcp: tools/list returned 6 tools to an anonymous client, including render_html (write), page_to_markdown (write), page_to_pdf (write)

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

No check matched anything in these tool definitions. That is not a safety guarantee.

History

Changes to its tool definitions and to its remote endpoint, newest first.

No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.

Install

Pinned to version 1.0.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http argoshot https://api.argoshot.com/mcp --header 'Authorization: <your-authorization>'
claude mcp add --transport http argoshot https://api.argoshot.com/mcp --header 'Authorization: <your-authorization>'

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__argoshot__get_usage",
      "mcp__argoshot__list_devices"
    ],
    "ask": [
      "mcp__argoshot__screenshot_url",
      "mcp__argoshot__render_html",
      "mcp__argoshot__page_to_markdown",
      "mcp__argoshot__page_to_pdf"
    ],
    "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 argoshot. Review it before you use it.

Capability tags behind 4 rules
  • mcp__argoshot__screenshot_url private-data, untrusted-input, outbound
  • mcp__argoshot__render_html untrusted-input
  • mcp__argoshot__page_to_markdown untrusted-input, outbound
  • mcp__argoshot__page_to_pdf untrusted-input, outbound

Pin

Keep the decision: fail CI when the tools change, follow every change, or show a badge.

Pin in CI

Fail a build when the tools you reviewed are not the tools the server serves today.

curl -s "https://radar.anlyon.com/api/v1/servers/io.github.rrlabs-io/argoshot/verify?hash=fb449d7738bb723f96e27f02cd6ca2aebaf9b2d6908b6ebd17fa878f7f4420fe" | jq -e '.changed == false'

Pinned hash fb449d7738bb, from Nov 18, 2026, 14:18 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/io.github.rrlabs-io/argoshot/changes.xml

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

Badge

Anlyon Radar badge for io.github.rrlabs-io/argoshot
[![Anlyon Radar](https://radar.anlyon.com/badge/io.github.rrlabs-io/argoshot.svg)](https://radar.anlyon.com/servers/io.github.rrlabs-io/argoshot)

Source: MCP Registry. Synced Nov 18, 2026, 15:18 UTC.

Argoshot MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the Argoshot MCP server safe?

No scan can promise that. What its definitions show: 6 tools, 3 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the Argoshot MCP server delete data?

No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.

Can the Argoshot MCP server do things that cannot be undone?

No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.

What tools does the Argoshot MCP server have?

6 tools: 3 write, 3 read. render_html, page_to_markdown, page_to_pdf, screenshot_url, get_usage and list_devices.

Does the Argoshot MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the Argoshot MCP server send data to outside services?

3 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): screenshot_url, page_to_markdown and page_to_pdf.

Has the Argoshot MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 18, 2026.