← Top 100 Full directory (1,580)

AgentScrape

Search & Web Remote ★ 571 6 tools

**Pay-per-call web scraping for AI agents — no signup, no API keys, just USDC.** AgentScrape is a production MCP server giving agents six paid tools for web scraping, structured extraction, screenshots, and metadata — all on Cloudflare Workers, all settled in USDC on Base via x402. ## Tools - **`scrape_webpage`** — fetch as markdown, html, text, or json - **`extract_structured_data`** — AI-powered extraction with natural-language prompts + JSON schemas - **`screenshot_webpage`** — PNG capture, viewport configurable - **`extract_metadata`** — OG, Twitter Card, JSON-LD - **`create_browser_session`** — persistent sessions for multi-step flows - **`run_workflow`** — multi-step atomic execution ## Pricing $0.001–$0.008 USDC per call on Base mainnet. No subscriptions. No API keys. Pay per request via x402. **Free tier:** 10 calls per wallet per 30 days. No signup required. ## Stack Cloudflare Workers · Hono · `@x402/hono` v2 · MCP Streamable HTTP · xpay.sh facilitator · Browser Rendering MIT licensed. Built by HSH Intelligence.

Connect

MCP endpoint

https://agentscrape--hshintelligence.run.tools

How to connect

Smithery (hosted)

1. Open https://smithery.ai/servers/hshintelligence/agentscrape
2. Click Connect and complete OAuth in your MCP client (Claude, Cursor, VS Code, etc.)
3. MCP endpoint: https://agentscrape--hshintelligence.run.tools

Tools (6)

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.