Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

Puptra PDF Snapshot

REMOTE · PUPTRA-PDF-SNAPSHOT.SAASTEMLY.COM · SCANNED OCT 2

One-call URL-to-PDF and full-page screenshot API with Puppeteer's page.pdf()/page.screenshot()...

52 Trust /100
Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →

Endpoint Security46
Transport & Reachability100
Schema Quality & AI Usability45
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 1553 tokens (~310/item across 5 items; 5 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management3
  • Stability observed for 1 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage78
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 33% of tool parameters carry a description.Partial
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 5 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 6 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities60
  • Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28. See how to fix → Fail
Install

How do I install the Puptra PDF Snapshot MCP server?

Puptra PDF Snapshot is a hosted endpoint at https://puptra-pdf-snapshot.saastemly.com/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

remote · puptra-pdf-snapshot.saastemly.com

# add to Claude Code
claude mcp add --transport http com-saastemly-puptra-pdf-snapshot 'https://puptra-pdf-snapshot.saastemly.com/mcp'
// .cursor/mcp.json
{
  "mcpServers": {
    "com-saastemly-puptra-pdf-snapshot": {
      "url": "https://puptra-pdf-snapshot.saastemly.com/mcp"
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "com-saastemly-puptra-pdf-snapshot": {
      "type": "http",
      "url": "https://puptra-pdf-snapshot.saastemly.com/mcp"
    }
  }
}
# ~/.codex/config.toml
[mcp_servers.com-saastemly-puptra-pdf-snapshot]
url = "https://puptra-pdf-snapshot.saastemly.com/mcp"
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-saastemly-puptra-pdf-snapshot": {
      "type": "remote",
      "url": "https://puptra-pdf-snapshot.saastemly.com/mcp",
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add com-saastemly-puptra-pdf-snapshot --url 'https://puptra-pdf-snapshot.saastemly.com/mcp' --transport streamable-http
# ~/.hermes/config.yaml
mcp_servers:
  com-saastemly-puptra-pdf-snapshot:
    url: "https://puptra-pdf-snapshot.saastemly.com/mcp"
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "com-saastemly-puptra-pdf-snapshot": {
      "Transport": "http",
      "Url": "https://puptra-pdf-snapshot.saastemly.com/mcp"
    }
  }
}
# add to Vellum
assistant mcp add com-saastemly-puptra-pdf-snapshot -t streamable-http -u 'https://puptra-pdf-snapshot.saastemly.com/mcp'
// mcp.json
{
  "mcpServers": {
    "com-saastemly-puptra-pdf-snapshot": {
      "type": "http",
      "url": "https://puptra-pdf-snapshot.saastemly.com/mcp"
    }
  }
}

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 2 Oct 26 +1
    • Stability: unverified → 0.03 ▲ functional
  • 1 Oct 26 51

    First indexed and scored.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 2 Oct 2026 · Probed https://puptra-pdf-snapshot.saastemly.com/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=saastemly.com CN=WE1,O=Google Trust Services,C=US 1 Oct 2026 30 Dec 2026 ECDSA 256 ECDSA-SHA256 6ce282d25a97fff0e07442a1c587009
SANs: saastemly.com, puptra-pdf-snapshot.saastemly.com, *.puptra-pdf-snapshot.saastemly.com
CN=WE1,O=Google Trust Services,C=US (CA) CN=GTS Root R4,O=Google Trust Services LLC,C=US 13 Dec 2023 20 Feb 2029 ECDSA 256 ECDSA-SHA384 7ff31977972c224a76155d13b6d685e3
CN=GTS Root R4,O=Google Trust Services LLC,C=US (CA) CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE 15 Nov 2023 28 Jan 2028 ECDSA 384 SHA256-RSA 7fe530bf331343bedd821610493d8a1b

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of puptra-pdf-snapshot.saastemly.com. — Not signed

Zone DS Keys Algorithms Outcome
. trust_anchor 20326, 38696 8, 8 Verified
com. present 19718 13 Verified
saastemly.com. absent Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication No authorisation required

The endpoint answered without asking for a token. Anyone who knows the URL can reach it.

Result No authorisation required
HTTP status 200

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://puptra-pdf-snapshot.saastemly.com/mcp Verified 200
http (plaintext) http://puptra-pdf-snapshot.saastemly.com/mcp Inconclusive 405
MCP tools · 5 exposed · ~1,470 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
links ~248

Every link on the page as absolute URLs, with optional same-domain-only and visible-only filters. Price: $0.005 a call.

NameTypeReqDescription
addScriptTagarray––
addStyleTagarray––
allowRequestPatternarray––
allowResourceTypesarray––
authenticateobject––
bestAttemptboolean––
cookiesarray––
emulateMediaTypestring––
excludeExternalLinksboolean–Only same-origin links (default false)
gotoOptionsobject––
htmlstring–HTML to render instead of a URL.
rejectRequestPatternarray––
rejectResourceTypesarray––
setExtraHTTPHeadersobject––
setJavaScriptEnabledboolean––
urlstring–The page (https). Set url or html, not both.
userAgentstring––
viewportobject––
visibleLinksOnlyboolean–Only links visible on the page (default false)
waitForSelectorobject––
waitForTimeoutnumber––

No output schema declared.

No examples provided.

markdown ~203

The page's rendered content as Markdown. Price: $0.005 a call.

NameTypeReqDescription
addScriptTagarray––
addStyleTagarray––
allowRequestPatternarray––
allowResourceTypesarray––
authenticateobject––
bestAttemptboolean––
cookiesarray––
emulateMediaTypestring––
gotoOptionsobject––
htmlstring–HTML to render instead of a URL.
rejectRequestPatternarray––
rejectResourceTypesarray––
setExtraHTTPHeadersobject––
setJavaScriptEnabledboolean––
urlstring–The page (https). Set url or html, not both.
userAgentstring––
viewportobject––
waitForSelectorobject––
waitForTimeoutnumber––

No output schema declared.

No examples provided.

pdf ~394

Render a URL or HTML to PDF with Puppeteer's page.pdf() options (format letter by default, scale, margins, header/footer templates, printBackground, pageRanges). Price: $0.005 a call.

NameTypeReqDescription
addScriptTagarray–[{content|url}]
addStyleTagarray–[{content|url}]
allowRequestPatternarray––
allowResourceTypesarray––
authenticateobject–{username,password}
bestAttemptboolean–Proceed when awaited events fail or time out
cookiesarray–Cookies to set before loading
deliverobject–{store: "1d"|"7d"|"30d"|"365d", name?}: keep the PDF in file storage and answer with metadata instead of bytes
emulateMediaTypestring–screen|print
gotoOptionsobject–{waitUntil: load|domcontentloaded|networkidle0|networkidle2, timeout}
htmlstring–HTML to render instead of a URL.
pdfOptionsobject–Puppeteer page.pdf() options as documented at pptr.dev/api/puppeteer.pdfoptions.
rejectRequestPatternarray––
rejectResourceTypesarray–e.g. ["image"]
setExtraHTTPHeadersobject–Extra HTTP headers
setJavaScriptEnabledboolean––
urlstring–The page to render (https). Set url or html, not both.
userAgentstring––
viewportobject–{width,height,deviceScaleFactor,isMobile,hasTouch,isLandscape}; default 1920x1080
waitForSelectorobject–{selector, visible?, hidden?, timeout}
waitForTimeoutnumber–Extra wait in ms (0-120000)

No output schema declared.

No examples provided.

screenshot ~334

Capture a PNG, JPEG or WebP screenshot with Puppeteer's page.screenshot() options (fullPage, clip, omitBackground, quality 0-100 for jpeg/webp only). Price: $0.005 a call.

NameTypeReqDescription
addScriptTagarray––
addStyleTagarray––
allowRequestPatternarray––
allowResourceTypesarray––
authenticateobject––
bestAttemptboolean––
cookiesarray––
deliverobject–{store, name?}: keep the image in file storage
emulateMediaTypestring––
gotoOptionsobject–{waitUntil, timeout}
htmlstring–HTML to render instead of a URL.
rejectRequestPatternarray––
rejectResourceTypesarray––
screenshotOptionsobject–Puppeteer page.screenshot() options as documented at pptr.dev/api/puppeteer.screenshotoptions.
scrollPageboolean–Scroll the page before capturing (lazy content)
selectorstring–Screenshot this element instead of the page
setExtraHTTPHeadersobject––
setJavaScriptEnabledboolean––
urlstring–The page to capture (https). Set url or html, not both.
userAgentstring––
viewportobject–{width,height,deviceScaleFactor,...}; default 1920x1080
waitForSelectorobject––
waitForTimeoutnumber––

No output schema declared.

No examples provided.

snapshot ~291

One call, several formats: rendered HTML content and a base64 screenshot (plus optional Markdown and accessibility tree), with the page's status and title. Price: $0.005 a call.

NameTypeReqDescription
addScriptTagarray––
addStyleTagarray––
allowRequestPatternarray––
allowResourceTypesarray––
authenticateobject––
bestAttemptboolean––
cookiesarray––
deliverobject–{store, name?}: keep the snapshot's screenshot in file storage
emulateMediaTypestring––
formatsarray–At least two of: content, screenshot, markdown, accessibilityTree (default content+screenshot)
gotoOptionsobject––
htmlstring–HTML to render instead of a URL.
rejectRequestPatternarray––
rejectResourceTypesarray––
screenshotOptionsobject–Puppeteer screenshot options for the snapshot's screenshot format
setExtraHTTPHeadersobject––
setJavaScriptEnabledboolean––
urlstring–The page to snapshot (https). Set url or html, not both.
userAgentstring––
viewportobject––
waitForSelectorobject––
waitForTimeoutnumber––

No output schema declared.

No examples provided.

Common questions

What is the Puptra PDF Snapshot MCP server?

Puptra PDF Snapshot is an MCP server listed in the public MCP registry as com.saastemly/puptra-pdf-snapshot. One-call URL-to-PDF and full-page screenshot API with Puppeteer's page.pdf()/page.screenshot()... This page covers its hosted endpoint (https://puptra-pdf-snapshot.saastemly.com/mcp).

Is the Puptra PDF Snapshot MCP server safe to use?

Puptra PDF Snapshot scores 52 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the Puptra PDF Snapshot MCP server expose?

Puptra PDF Snapshot exposes 5 tools: pdf, screenshot, snapshot, markdown, links. Their descriptions and schemas cost roughly 1,470 tokens of context every time the server is loaded.

Does the Puptra PDF Snapshot MCP server require authentication?

No. We connected to Puptra PDF Snapshot without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

Is the Puptra PDF Snapshot MCP server still maintained?

Puptra PDF Snapshot is still listed as active in the MCP registry. We last reached this channel on 2 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.