pagepixels-screenshots-mcp-server

A Model Context Protocol (MCP) server for the PagePixels Screenshot API. Enables AI assistants like Claude, Cursor, Windsurf, and other MCP-compatible clients to capture screenshots, manage screenshot configurations, monitor page changes, and perform AI-powered domain research — all through natural language.

Features

• Instant Screenshots — Capture any URL or render raw HTML to an image on demand

• Multi-Step Browser Actions — Click, type, submit forms, navigate pages, and wait for elements before capturing

• Scheduled Screenshots — Create recurring capture configurations on minute, hour, day, week, month, or year intervals

• Geo-Located Captures — Screenshot from 150+ real locations worldwide (countries, US states, and major cities)

• Change Notifications — Monitor pages for visual changes with Slack and webhook alerts

• Domain Research — AI-powered structured data extraction across multiple domains

• Full Configuration Management — Create, read, update, delete, and list screenshot configurations programmatically

• OAuth 2.1 Authentication — Secure, spec-compliant MCP auth via Streamable HTTP transport

Requirements

• A PagePixels account (free tier available — no payment info required)

Quick Start

Claude.ai

1. Open Settings (bottom-left) and navigate to Integrations

2. Select Add custom connector

3. Enter the server URL:

   https://mcp.pagepixels.com/mcp

4. Complete the OAuth authorization when prompted in the browser

Once connected, PagePixels tools will be available in all new conversations.

Cursor / Windsurf / Claude Desktop / Other MCP Clients

Connect over Streamable HTTP by pointing your client at:

https://mcp.pagepixels.com/mcp

For clients that support remote MCP servers with OAuth, authentication is handled via the standard MCP OAuth 2.1 flow with PKCE — authorize through the browser prompt when first connecting.

Tools

Screenshot Capture

Screenshot Configuration Management

Screenshot History

Change Notifications

Domain Research

Account & Utilities

Usage Examples

Once connected, interact naturally with your AI assistant:

Take a screenshot:

"Take a screenshot of https://example.com in PNG format at 1440px wide"

Multi-step capture:

"Go to https://example.com, click the login button, fill in the email field with test@example.com, submit the form, then take a full-page screenshot"

Scheduled monitoring:

"Create a screenshot configuration for https://example.com/pricing that captures every 6 hours as JPEG"

Geo-located capture:

"Screenshot https://example.com from Japan with a Retina scale factor"

Domain research:

"Research these 5 competitor domains and extract their pricing tiers, founding year, and team size"

Account overview:

"Show me my current usage and remaining credits"

Capture Options

The snap and snap_html tools support extensive configuration:

• Viewport: page_width, page_height, scale_factor (1x or 2x Retina)

• Output: image_format (jpeg, png, webp), quality (1–100 for JPEG), thumbnails

• Full Page: fullpage, fullpage_advanced, incremental_scroll for lazy-loaded content

• Timing: wait (ms delay before capture), wait_for (CSS selector to appear)

• Injection: js_inject, css_inject for custom page modifications

• Privacy: no_ads, no_cookie_banners, no_tracking

• Scripting: disable_js, disable_third_party_js

• Geo-Location: real_location (150+ locations), latitude/longitude, time_zone

• Auth & Headers: cookies, headers, user_agent

• Element Capture: selectors to capture a specific DOM element

• HTML Extraction: html_only to return fully rendered HTML instead of an image

• Caching: ttl to control cache duration (0 for always fresh)

Multi-Step Actions

Automate browser interactions before capturing with multi_step_actions:

[
  { "type": "click", "selector": "#login-btn" },
  { "type": "text_field", "selector": "#email", "value": "user@example.com" },
  { "type": "text_field", "selector": "#password", "value": "secret" },
  { "type": "submit" },
  { "type": "wait_for_selector", "selector": ".dashboard" }
]

Supported action types: click, hover, change, redirect, javascript, evaluateJs, css, text_field, select, checkbox, submit, wait, wait_for_selector

Authentication

Authentication is handled through the standard MCP OAuth 2.1 flow with PKCE. When connecting through Claude.ai, Cursor, or other OAuth-capable MCP clients, authorize through the browser prompt when first connecting. No manual API key configuration is needed.

For programmatic access outside of MCP, see the PagePixels API documentation.

Transport

This server uses the MCP Streamable HTTP transport, hosted at:

https://mcp.pagepixels.com/mcp

All MCP clients that support remote Streamable HTTP servers can connect directly. OAuth 2.1 with PKCE is enforced on all connections.

Related

• PagePixels Documentation — Full API reference

• screenshots-pagepixels — Node.js API client

• screenshots-pagepixels (PyPI) — Python API client

• screenshots_pagepixels (RubyGems) — Ruby API client

• Model Context Protocol — MCP specification

License

MIT