# Apiflash — how to use (mcp.ai)

Connect your Apiflash account and use 5 tools for images and design straight from your AI agent. Connect with your own API key. ApiFlash is a website screenshot API that allows users to capture high-quality screenshots of web pages programmatically.

## Option A — via MCP (recommended)
Remote MCP endpoint (HTTP, streamable): `https://api.mcp.ai/p_apiflash?ms=1787295960000`
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. `apiflash_batch_capture_screenshots`).

## Option B — via direct REST API
Base URL: `https://api.mcp.ai/api/apiflash`
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/apiflash/_endpoints`

### Endpoints
- `POST https://api.mcp.ai/api/apiflash/batch/capture/screenshots` — Tool to capture screenshots for multiple URLs in a single request. Use when you have a list of pages to snapshot in batch.
  - body: { urls: string[], fresh?: boolean, width?: integer, format?: string, height?: integer, full_page?: boolean }
- `POST https://api.mcp.ai/api/apiflash/capture/screenshot` — Tool to capture a screenshot of a website. Returns a JSON response with URLs to the screenshot (and optionally extracted HTML/text). Supports extensive customization including viewport dimensions, ful
  - body: { js?: string, css?: string, ttl?: integer, url: string, crop?: string, delay?: integer, fresh?: boolean, proxy?: string, width?: integer, format?: string, height?: integer, no_ads?: boolean, s3_key?: string, cookies?: string, element?: string, headers?: string, quality?: integer, accuracy?: integer, latitude?: number, wait_for?: string, full_page?: boolean, longitude?: number, s3_bucket?: string, s3_region?: string, time_zone?: string, user_agent?: string, wait_until?: string, ip_location?: string, no_tracking?: boolean, s3_endpoint?: string, scroll_page?: boolean, transparent?: boolean, extract_html?: boolean, extract_text?: boolean, scale_factor?: integer, response_type?: string, s3_secret_key?: string, fail_on_status?: string, accept_language?: string, element_overlap?: boolean, thumbnail_width?: integer, s3_access_key_id?: string, no_cookie_banners?: boolean }
- `POST https://api.mcp.ai/api/apiflash/capture/website/screenshot/post` — Capture a screenshot of any website. Returns a URL to the generated screenshot image. Supports full-page captures, custom viewport sizes, and multiple image formats (JPEG, PNG, WebP). Use this tool wh
  - body: { url: string, delay?: integer, fresh?: boolean, width?: integer, format?: string, height?: integer, quality?: integer, full_page?: boolean }
- `POST https://api.mcp.ai/api/apiflash/get/quota/information` — Tool to retrieve current API quota usage and limits. Use after authentication to monitor usage and reset times.
- `POST https://api.mcp.ai/api/apiflash/get/screenshot/metadata` — Retrieve metadata (file size, MIME type) for a previously captured screenshot. Use this tool when you need to check the size or format of a screenshot without downloading the full image. Requires the 
  - body: { url: string }

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

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