# Screenshot API — MCP server on mcp.ai
> Connect your Screenshot API account and use 5 tools for images and design straight from your AI agent. Connect with your own API key. Screenshot API renders webpages and custom HTML as images, PDFs, videos, or extracted content and supports paid asynchronous bulk capture jobs.

By: mcp.ai · official
Page: https://mcp.ai/screenshot_api

## Connect (MCP protocol)
Remote MCP endpoint (HTTP, streamable): https://api.mcp.ai/p_screenshot_api?ms=1787296080000
Add it as a custom/remote MCP connector, then authenticate when prompted.

## REST API (no MCP client required)
Every tool is also a REST endpoint, authed with a workspace API key.
Discover: GET https://api.mcp.ai/api/screenshot_api/_endpoints   # public; lists every endpoint
Call:     POST https://api.mcp.ai/api/screenshot_api/<endpoint>
  Authorization: Bearer sk_live_…   # create one at https://mcp.ai/settings/api-keys
  Content-Type: application/json
  Body: { …args }   →   { "ok": true, "tool": "<id>", "result": { … } }

## Developer docs
How to use (MCP or REST), markdown: https://mcp.ai/screenshot_api/skill.md
Postman collection (v2.1): https://mcp.ai/screenshot_api/postman.json

## Tools
- screenshot_api_create_bulk_csv_job(csv_file: object) — Upload a CSV file to start a paid asynchronous bulk screenshot job and return the provider's complete job acceptance payload containing its UUID.
- screenshot_api_create_bulk_json_job(urls: object[]) — Start a paid asynchronous bulk screenshot job from up to 50 JSON request items and return the provider's complete job acceptance payload containing its UUID.
- screenshot_api_download_bulk_results(job_uuid: string) — Download the processed result CSV for a completed paid bulk screenshot job UUID.
- screenshot_api_get_bulk_job_status(job_uuid: string) — Get progress and success/failure counts for a paid asynchronous bulk screenshot job UUID.
- screenshot_api_render_screenshot(url: string, cache?: object, storage?: object, blocking?: object, viewport?: object, file_type?: string, page_load?: object, scrolling?: object, appearance?: object, extraction?: object, custom_html?: string, pdf_options?: object, browser_context?: object) — Render a webpage or custom HTML and return a stored image, PDF, or video URL plus optional extracted content links. A custom result filename can replace an existing stored file with the same name.

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

## Links
Docs: https://mcp.ai/docs/mcps/screenshot_api
Website: https://mcp.ai/mcps/screenshot_api