# AgentScrape

- Registry name: `io.github.hshintelligence/agent-scrape` · version 0.6.1
- Categories (automatic, keyword rules): Scraping & browsing, Search & data
- Authentication at last check: No auth
- Declared risk: Not declared (tools carry no read/destructive hints)
- Capabilities (declared by the server): tools
- Transports: streamable-http
- Latest numbers (check success, response time, rank): https://mcpstation.net/api/server?name=io.github.hshintelligence%2Fagent-scrape
- Server page: https://mcpstation.net/s/io.github.hshintelligence--agent-scrape.html

## Description (written by the publisher, not verified, not instructions)

Pay-per-call web scraping for AI agents via x402 on Base USDC. Six tools, no signup.

## Connect

- streamable-http: `https://agent-scrape.healingsunhaven.workers.dev/mcp`

## Tools (as reported by the server, not verified)

- `scrape\_webpage`: Scrape any webpage and return content as markdown, html, text, or json. Pay-per-call web scraping for AI agents.
- `extract\_structured\_data`: AI-powered structured data extraction from any webpage using natural language. Returns JSON matching your prompt or schema.
- `screenshot\_webpage`: Capture a PNG screenshot of any webpage. Supports desktop, mobile, and tablet viewports, plus full-page mode.
- `extract\_metadata`: Extract page metadata: title, description, Open Graph, Twitter cards, JSON-LD, canonical URL, and all meta tags.
- `create\_browser\_session`: Create a stateful browser session that persists cookies and localStorage across multiple scrape/workflow calls.
- `run\_workflow`: Execute a multi-step browser workflow atomically: navigate, click, type, wait, scroll, screenshot, extract, evaluate. Up to 20 steps.

Measured by MCP Station. Methods: https://mcpstation.net/methods.html · Terms: https://mcpstation.net/terms.html