# Webscraper io — how to use (mcp.ai)

Connect your Webscraper io account and use 10 tools for developer tools straight from your AI agent. Connect with your own API key. WebScraper.IO is a web scraping tool that makes web data extraction easy and accessible for everyone through a cloud-based API.

## Option A — via MCP (recommended)
Remote MCP endpoint (HTTP, streamable): `https://api.mcp.ai/p_webscraper_io?ms=1787293440000`
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. `webscraper_io_create_sitemap`).

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

### Endpoints
- `POST https://api.mcp.ai/api/webscraper_io/create/sitemap` — Tool to create a new sitemap configuration for web scraping. Use when you need to define a new scraping structure with start URLs and selector rules for data extraction from a website.
  - body: { startUrl: string[], selectors: object[], sitemap_id: string }
- `POST https://api.mcp.ai/api/webscraper_io/delete/sitemap` — Tool to permanently delete a sitemap configuration from Web Scraper Cloud account. Use when you need to remove a sitemap that is no longer needed.
  - body: { sitemap_id: integer }
- `POST https://api.mcp.ai/api/webscraper_io/disable/sitemap/scheduler` — Tool to disable automatic scheduling for a sitemap. Use when you need to stop automated scraping jobs from running on a schedule.
  - body: { sitemap_id: integer }
- `POST https://api.mcp.ai/api/webscraper_io/enable/sitemap/scheduler` — Tool to enable and configure automatic scheduling for sitemap scraping jobs. Use when you need to automate scraping jobs to run at specific times using cron expressions with customizable request inter
  - body: { proxy?: string|integer, driver: string, cron_day: string, cron_hour: string, cron_month: string, sitemap_id: integer, cron_minute: string, cron_weekday: string, cron_timezone: string, page_load_delay: integer, request_interval: integer }
- `POST https://api.mcp.ai/api/webscraper_io/get/account/info` — Tool to retrieve account information including email and page credits. Use when you need to check account details or available credits.
- `POST https://api.mcp.ai/api/webscraper_io/get/scraping/jobs` — Tool to retrieve all scraping jobs for the account with optional filtering and pagination. Use when you need to list scraping jobs, check job status, or filter jobs by sitemap or tag.
  - body: { tag?: string, page?: integer, sitemap_id?: integer }
- `POST https://api.mcp.ai/api/webscraper_io/get/sitemap` — Tool to retrieve a specific sitemap configuration by ID. Use when you need to inspect or reference an existing sitemap's configuration.
  - body: { sitemap_id: integer }
- `POST https://api.mcp.ai/api/webscraper_io/get/sitemap/scheduler` — Tool to retrieve scheduler configuration for a sitemap. Use when you need to check scheduling settings including cron configuration and proxy settings.
  - body: { sitemap_id: integer }
- `POST https://api.mcp.ai/api/webscraper_io/get/sitemaps` — Tool to retrieve all sitemaps for the authenticated account with pagination support. Use when you need to list available sitemaps or filter them by tag. Supports optional pagination via page parameter
  - body: { tag?: string, page?: integer }
- `POST https://api.mcp.ai/api/webscraper_io/update/sitemap` — Tool to update an existing sitemap configuration including structure, URLs, and selectors. Use when you need to modify sitemap settings.
  - body: { _id: string, selectors: object[], start_url: string[], sitemap_id: integer }

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

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