About Pagewatch
Pagewatch is an MCP server that gives agents browser-rendered web content as Markdown, screenshots, or PDFs. It also provides key management and can be used locally or through a hosted endpoint.
Key features
- 01Convert URLs to clean Markdown
- 02Capture rendered pages as PNG
- 03Create PDFs from URLs or HTML
- 04Register and check API keys
- 05Run locally or use hosted endpoint
Use cases
- 01Read JavaScript-rendered pages
- 02Capture a page for visual review
- 03Create a PDF from a URL or HTML
MCP support
Exposes page reading, screenshot, PDF, and key-management tools to MCP clients. Available as a local stdio server or a hosted remote MCP server.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://pagelens.dev/mcpclaude mcp add --transport http dev-pagelens-pagewatch https://pagelens.dev/mcp{"mcpServers":{"dev-pagelens-pagewatch":{"type":"http","url":"https://pagelens.dev/mcp"}}}Open in Cursor{"servers":{"dev-pagelens-pagewatch":{"type":"http","url":"https://pagelens.dev/mcp"}}}Open in VS Code{"mcpServers":{"dev-pagelens-pagewatch":{"type":"http","url":"https://pagelens.dev/mcp"}}}{"mcpServers":{"dev-pagelens-pagewatch":{"serverUrl":"https://pagelens.dev/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
Details
From the project READMEmcp-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.
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.
Install
Add this to your MCP client config:
{
"mcpServers": {
"pagewatch": {
"command": "uvx",
"args": ["pagewatch-mcp"]
}
}
}
That is it. uv fetches the package on first run, and your first tool call returns real content.
Or install it yourself with pip:
pip install 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 |
|---|---|---|
PAGEWATCH_API_KEY | none | An existing key. Without one, the first call mints a free trial key and hands it back. |
PAGEWATCH_BASE_URL | https://pagelens.dev | Point at a different pagewatch deployment. |
PAGEWATCH_MCP_TRANSPORT | stdio | Set to http to serve streamable-http on $PORT instead. |
PAGEWATCH_SOURCE | mcp-selfhost | Attribution tag recorded when a key is registered. |
What this package does and does not do
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. You can read the whole thing in a couple of minutes and
know exactly what it sends and where.
Docker
docker build -t pagewatch-mcp .
docker run --rm -i pagewatch-mcp
License
MIT
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.