loading…
Search for a command to run...
loading…
Enables AI assistants to capture website screenshots, automate browser interactions, and manage recurring screenshot configurations across 150+ global locations
Enables AI assistants to capture website screenshots, automate browser interactions, and manage recurring screenshot configurations across 150+ global locations. It also supports AI-powered domain research and visual change monitoring for any web page.
A Model Context Protocol (MCP) server for the PagePixels Screenshot API. Enables AI assistants to capture instant and scheduled screenshots, generate images from raw HTML, take screenshots after performing browser actions, and run AI-powered website domain research using natural language.
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.
https://mcp.pagepixels.com/mcp
Once connected, PagePixels tools will be available in all new conversations.
| Tool | Description |
|---|---|
snap |
Capture a screenshot of any URL with full control over viewport, format, quality, wait conditions, JS/CSS injection, multi-step browser actions, AI analysis, and geo-location |
snap_html |
Render raw HTML content into a screenshot with the same capture options as snap |
capture_screenshot |
Trigger an immediate capture for an existing screenshot configuration |
| Tool | Description |
|---|---|
create_screenshot_config |
Create a new configuration with optional scheduling (minutes through years) |
get_screenshot_config |
Retrieve a configuration by ID |
update_screenshot_config |
Update any property of an existing configuration |
delete_screenshot_config |
Delete a configuration and all its captured screenshots |
list_screenshot_configs |
List all configurations in the account with pagination and time filters |
| Tool | Description |
|---|---|
list_config_screenshots |
List all screenshots for a specific configuration |
list_all_screenshots |
List all screenshots across the account |
| Tool | Description |
|---|---|
list_config_change_notifications |
List change notifications for a specific configuration |
list_all_change_notifications |
List all change notifications across the account |
| Tool | Description |
|---|---|
create_domain_research |
Submit an AI-powered data extraction job across one or more domains with custom field definitions |
get_domain_research_status |
Check the status of a domain research job |
get_domain_research_report |
Download completed research results as JSON or CSV |
list_domain_research_reports |
List all domain research reports in the account |
| Tool | Description |
|---|---|
analyze_any_image_with_ai |
Submit up to 5 images and 5 prompts for an AI to analyze |
| Tool | Description |
|---|---|
get_account_limits |
Get current usage and account limits |
get_job_status |
Check if a screenshot job has completed |
list_real_locations |
List all 150+ supported geo-locations for screenshot capture |
Once connected, interact naturally with your AI assistant:
Take a screenshot:
"Take a screenshot of https://example.com in PNG format at 540px wide and remove cookie banners"
Multi-step capture:
"Go to https://example.com, click the login button, fill in the email field with [email protected], 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"
Geo-located capture:
"Screenshot https://example.com from Japan and wait 6000ms before taking the screenshot"
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"
The snap and snap_html tools support extensive configuration:
page_width, page_height, scale_factor (1x or 2x Retina)image_format (jpeg, png, webp), quality (1–100 for JPEG), thumbnailsfullpage, fullpage_advanced, incremental_scroll for lazy-loaded contentwait (ms delay before capture), wait_for (CSS selector to appear)js_inject, css_inject for custom page modificationsno_ads, no_cookie_banners, no_trackingreal_location (150+ locations)analyze_image_with_ai and ai_prompt to analyze a screenshot guided by a custom text promptcookies, headersselectors to capture a specific DOM elementhtml_only to return fully rendered HTML instead of an imagettl to control cache duration (0 for always fresh)See full list of screenshot options.
Automate browser interactions before capturing with multi_step_actions:
[
{ "type": "click", "selector": "#login-btn" },
{ "type": "text_field", "selector": "#email", "value": "[email protected]" },
{ "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 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.
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.
MIT
Добавь это в claude_desktop_config.json и перезапусти Claude Desktop.
{
"mcpServers": {
"pagepixels-screenshots-mcp-server": {
"command": "npx",
"args": []
}
}
}