pagewatch-mcp
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@pagewatch-mcp Read https://example.com and return as markdown"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
mcp-name: dev.pagelens/pagewatch
pagewatch-mcp
An MCP server that gives an agent a real browser. Three tools:
read_pageturns any url into clean markdownscreenshotreturns a png of the rendered pagepdfturns a url or raw html into a pdf
Plus register and balance for managing your key.
It runs javascript, so it works on pages that a plain http fetch returns empty. It respects robots.txt and refuses sites that block automation instead of trying to defeat them.
This is the Node build. There is an identical Python one on PyPI, also called
pagewatch-mcp.
No signup
Your first call mints a free trial key and returns real content. There is no form for your agent to get stuck on. When the trial runs out, one email confirmation by a human unlocks 200 more free credits, still free.
Billing is metered, but there is no payment processor connected right now, so nothing is ever charged.
Related MCP server: WebScrape MCP Server
Install
Add this to your MCP client config:
{
"mcpServers": {
"pagewatch": {
"command": "npx",
"args": ["-y", "pagewatch-mcp"]
}
}
}That is it. npm fetches the package on first run, and your first tool call returns real content. Node 18 or newer.
Or install it yourself:
npm install -g pagewatch-mcp{
"mcpServers": {
"pagewatch": { "command": "pagewatch-mcp" }
}
}Already hosted
If you would rather not run anything, the same tools are live at
https://pagelens.dev/mcp as a remote MCP server.
Configuration
Everything is optional.
Variable | Default | What it does |
| none | An existing key. Without one, the first call mints a free trial key and hands it back. |
|
| Point at a different pagewatch deployment. |
|
| Attribution tag recorded when a key is registered. |
What is in this package
It is deliberately thin. Every tool is one https call to a documented /v1 route
on the pagewatch API. There is no browser, no scraping logic and no credential
store in this package. The whole server is one file, index.js. You can read it in
a couple of minutes and know exactly what it sends and where. The only dependency
is the official MCP SDK.
License
MIT
Available Tools
5 toolsbalanceA
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 set PAGEWATCH_API_KEY.
api_key: an existing pagewatch bearer token, optional.
Inputs: api_key.
pdfA
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.
Inputs: url, html, paper, api_key, +1 more.
read_pageA
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.
Inputs: url (required), scroll, api_key, wait_for_selector.
registerA
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 PAGEWATCH_API_KEY. 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.
Inputs: label, purpose.
screenshotA
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.
Inputs: url (required), width, format, height, +3 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 5 tools
Each tool serves a distinct purpose: read_page returns markdown content, screenshot returns an image, pdf returns a PDF, register creates an API key, and balance checks credits. No overlap between tools.
Names are all lowercase and use clear terms, but there is slight inconsistency: read_page uses an underscore while screenshot, pdf, register, and balance are single words. The pattern is still predictable and readable.
With 5 tools covering web page extraction (content, screenshot, pdf) and account management (register, balance), each tool earns its place without being excessive or insufficient.
The tool surface fully covers the domain: fetching web content in multiple formats, plus account registration and credit checking. No obvious gaps within the service's scope.
Related MCP Connectors
A real browser for your agent: screenshots, page checks, Markdown and PDFs.
Web scraping, browser automation, screenshots and AI data extraction for AI agents via MCP.
Turn any public website into an MCP server for agents to search, read and navigate.
Official Browserless MCP server: browser automation, scraping, screenshots and PDFs for AI agents.
Related MCP Servers
- AlicenseAqualityDmaintenanceAn MCP server that fetches web pages and extracts clean, AI-friendly Markdown content using Mozilla Readability. It provides secure web access for LLMs with built-in SSRF protection and automated content cleaning for improved context retrieval and summarization.180 npmMIT
- FlicenseNot gradedqualityDmaintenanceMCP server that enables AI agents to search the web and extract clean Markdown content, with support for JavaScript rendering, structured data extraction, and screenshots.2-
- FlicenseNot gradedqualityCmaintenanceMCP server that converts web pages to clean Markdown for LLMs via two paid tools: surface_markdown_parser and stealth_markdown_parser.-
- AlicenseNot gradedqualityCmaintenanceA public MCP server that lets AI agents read live web pages as clean Markdown, with tools to fetch, search, extract metadata, and extract links from URLs.1MIT