# ScreenshotOne — how to use (mcp.ai)

Connect your ScreenshotOne account and use 5 tools for developer tools straight from your AI agent. Connect with your own API key. ScreenshotOne is a screenshot API for developers, enabling the rendering of website screenshots through simple API calls without managing browser clusters.

## Option A — via MCP (recommended)
Remote MCP endpoint (HTTP, streamable): `https://api.mcp.ai/p_screenshotone?ms=1787296020000`
Add it as a custom/remote MCP connector in your client (Claude, Cursor, VS Code…), then authenticate when prompted. Once connected, ask the agent to use the server's tools (e.g. `screenshotone_get_usage`).

## Option B — via direct REST API
Base URL: `https://api.mcp.ai/api/screenshotone`
Auth: `Authorization: Bearer sk_live_…` — create a workspace API key at https://mcp.ai/settings/api-keys
Discover endpoints: `GET https://api.mcp.ai/api/screenshotone/_endpoints`

### Endpoints
- `POST https://api.mcp.ai/api/screenshotone/get/usage` — Tool to retrieve current API plan usage information. Returns total requests allowed, available requests remaining, used requests count, and concurrency limits for the current billing period.
- `POST https://api.mcp.ai/api/screenshotone/list/devices` — Tool to retrieve the list of supported devices for viewport emulation. Use when you need to get available device IDs and their viewport configurations for device emulation in screenshot operations.
- `POST https://api.mcp.ai/api/screenshotone/take/animated/screenshot` — This tool captures an animated screenshot (video or GIF) of a given website URL. It allows customization of the animation format, duration, viewport dimensions, and animation scenario (e.g., scrolling
  - body: { url: string, delay?: integer, width?: integer, clip_x?: integer, clip_y?: integer, format?: string, height?: integer, duration?: integer, scenario?: string, block_ads?: boolean, full_page?: boolean, scroll_by?: integer, clip_width?: integer, clip_height?: integer, scroll_back?: boolean, aspect_ratio?: string, scroll_delay?: integer, scroll_easing?: string, viewport_width?: integer, omit_background?: boolean, scroll_complete?: boolean, scroll_duration?: integer, viewport_height?: integer, scroll_start_delay?: integer, device_scale_factor?: number, scroll_to_end_after?: integer, scroll_try_navigate?: boolean, block_cookie_banners?: boolean, scroll_till_selector?: string, scroll_back_algorithm?: string, scroll_navigate_after?: integer, scroll_navigate_to_url?: string, scroll_start_immediately?: boolean, scroll_back_after_duration?: integer, scroll_navigate_link_hints?: string[], scroll_stop_after_duration?: integer, scroll_till_selector_adjust_top?: integer }
- `POST https://api.mcp.ai/api/screenshotone/take/bulk/screenshots` — Tool to take multiple screenshots in a single request with shared defaults and individual overrides. Use when you need to capture screenshots of multiple URLs or the same URL with different parameters
  - body: { execute?: boolean, options?: object, optimize?: boolean, requests: object[] }
- `POST https://api.mcp.ai/api/screenshotone/take/screenshot` — Tool to generate a screenshot or PDF of a website, render HTML, or Markdown using POST request. Use when you need to capture webpage content in various formats (PNG, JPEG, WebP, PDF, HTML). Supports b
  - body: { url?: string, html?: string, cache?: boolean, delay?: integer, format?: string, markdown?: string, block_ads?: boolean, dark_mode?: boolean, block_chats?: boolean, response_type?: string, viewport_width?: integer, viewport_height?: integer, device_scale_factor?: integer, block_cookie_banners?: boolean }

## Example prompts
- "What can I do in ScreenshotOne?"
- "Show me a summary of my ScreenshotOne account"

## More
- Page: https://mcp.ai/screenshotone
- Agent spec (llms.txt): https://mcp.ai/screenshotone/llms.txt
- Postman collection: https://mcp.ai/screenshotone/postman.json