Skip to content

Pagewatch

by pagelens.dev · remote · local (npm, pypi) · no sign-in to list tools · v0.2.3 · published by dev.pagelens

Read a URL as clean markdown, screenshot a website, url to PDF. Web access for agents, no signup.

Changes · 3
CompareRegistry entry

5 tools: 3 change things and 2 only read.

Scanned Oct 21, 2026

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

claude mcp add --transport http pagewatch https://pagelens.dev/mcp

Tools

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

5 tools

Changes things 3Claude Code: ask
  • balanceCheck the remaining free credits on your pagewatch key, plus the per-call prices and, if the key is not switched on yet, the free activation link to give your human.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Check the remaining free credits on your pagewatch key, plus the per-call prices and, if the key is not switched on yet, the free activation link to give your human. Pass api_key if you did not configure an Authorization header. api_key: an existing pagewatch bearer token, optional.
  • pdfRender a web page (by url) or raw html into a pdf and return it as base64 pdf data.Can 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.

    What it can reach

    • 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
    Render a web page (by url) or raw html into a pdf and return it as base64 pdf data. Provide exactly one of url or html. Respects robots.txt for url input. Pass api_key if you have a pagewatch key, otherwise a free trial key is created for you and returned. url: the page to convert, optional. html: raw html to convert, optional (provide url or html, not both). api_key: an existing pagewatch bearer token, optional. paper: A4, Letter, Legal or A3. landscape: landscape orientation.
  • registerCreate a pagewatch api key for yourself.No findings

    Why it is in this group

    • The description's first verb is "create": a word for a change.
    Description, as the server wrote it
    Create a pagewatch api key for yourself. Free, no signup and no human form. Returns a bearer token that starts with a small free trial so your first read_page, screenshot or pdf works right away. When the trial runs out, hand the returned verification_uri_complete to your human, who confirms one email to unlock 200 more free credits (still free, nothing to pay). Reuse the token by passing it as api_key, or set it as Authorization: Bearer <token> on this server. Nothing is ever charged: pagewatch has no payment processor connected. label: a short name for this key, optional. purpose: why you want web access, shown to your human on the activation page.
Only reads 2Claude Code: allow, ask for 2 outbound
  • read_pageLoad a web page in a real browser and return its main content as clean markdown, with the title, canonical url and basic metadata.Reads text others writeCan send data outNo findings

    Why it is in this group

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

    What it can reach

    • 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
    Load a web page in a real browser and return its main content as clean markdown, with the title, canonical url and basic metadata. Handles javascript-rendered pages. Respects robots.txt and refuses sites that block automation rather than trying to defeat them. Pass api_key if you already have a pagewatch key, otherwise a free trial key is created for you on the first call and returned in the response. url: the page to read (http or https). api_key: an existing pagewatch bearer token, optional. wait_for_selector: css selector to wait for before reading, optional. scroll: scroll the page to trigger lazy-loaded content, optional.
  • screenshotTake a screenshot of a web page rendered in a real browser and return it as base64 image data (png by default, jpeg optional), with the final url and pixel size.Reads text others writeCan send data outNo findings

    Why it is in this group

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

    What it can reach

    • 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
    Take a screenshot of a web page rendered in a real browser and return it as base64 image data (png by default, jpeg optional), with the final url and pixel size. Consent overlays are hidden so the shot shows the page. Respects robots.txt. Pass api_key if you have a pagewatch key, otherwise a free trial key is created for you and returned. url: the page to capture. api_key: an existing pagewatch bearer token, optional. full_page: capture the entire scrollable page, not just the viewport. width, height: viewport size in pixels. format: png or jpeg. wait_for_selector: css selector to wait for before capturing, optional.

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 out3
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, 14:46 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
3
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 3 tools that change things (3 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://pagelens.dev/mcp: tools/list returned 5 tools to an anonymous client, including pdf (write), register (write), balance (write)

    What this check looks for

Install

Pinned to version 0.2.3. Values in angle brackets are yours to fill in.

claude mcp add --transport http pagewatch https://pagelens.dev/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__pagewatch__read_page",
      "mcp__pagewatch__screenshot",
      "mcp__pagewatch__pdf",
      "mcp__pagewatch__register",
      "mcp__pagewatch__balance"
    ],
    "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 pagewatch. Review it before you use it.

Capability tags behind 3 rules
  • mcp__pagewatch__read_page untrusted-input, outbound
  • mcp__pagewatch__screenshot untrusted-input, outbound
  • mcp__pagewatch__pdf outbound