# CaptureKit — how to use (mcp.ai)

Connect your CaptureKit account and use 5 tools for developer tools straight from your AI agent. Connect with your own API key. CaptureKit captures webpage screenshots, extracts structured web content, crawls pages, and analyzes websites with AI.

## Option A — via MCP (recommended)
Remote MCP endpoint (HTTP, streamable): `https://api.mcp.ai/p_capturekit?ms=1787291160000`
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. `capturekit_analyze_webpage`).

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

### Endpoints
- `POST https://api.mcp.ai/api/capturekit/analyze/webpage` — Analyze a webpage with AI to identify its summary, value proposition, features, categories, use cases, audience, and optional custom fields.
  - body: { url: string, custom_fields?: object, custom_prompt?: string }
- `POST https://api.mcp.ai/api/capturekit/capture/webpage` — Capture a webpage as an image or PDF and return a downloadable file reference.
  - body: { url: string, delay?: number, device?: string, format?: string, selector?: string, full_page?: boolean, remove_ads?: boolean, wait_until?: string[], viewport_width?: integer, viewport_height?: integer, remove_selectors?: string[], wait_for_selector?: string, remove_cookie_banners?: boolean }
- `POST https://api.mcp.ai/api/capturekit/extract/webpage/content` — Extract webpage metadata and links, optionally including rendered HTML, Markdown, sitemap data, or cleaned main content.
  - body: { url: string, delay?: number, remove_ads?: boolean, wait_until?: string[], include_html?: boolean, use_defuddle?: boolean, include_sitemap?: boolean, include_markdown?: boolean, remove_selectors?: string[], wait_for_selector?: string, remove_cookie_banners?: boolean }
- `POST https://api.mcp.ai/api/capturekit/fetch/page/html` — Fetch a webpage's raw HTML without browser rendering for fast scraping, audits, or monitoring.
  - body: { url: string, allow_redirects?: boolean }
- `POST https://api.mcp.ai/api/capturekit/get/usage` — Return the connected workspace's current CaptureKit allowance, usage, API-key status, quotas, and effective rate limits.

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

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