claude mcp add agent-scraper-mcp -- npx -y agent-scraper-mcp
A pasteable skeleton generated from the repository name. Check the project README for the exact package and arguments.
Star count
8 ★ · aparajithn/agent-scraper-mcp · read from the repository page · (checked 2026-10-16 20:00:20)
Source
collected from the punkpeye/awesome-mcp-servers list · type: MCP server
Harvest history
first seen 2026-10-09 · last seen 2026-10-16 · seen 32× · listed by 7 sources
Score
score 703 · 8 ★ · 7 sources · mcp
FAQ (answers come from our records)
How do I install it?
We did not find an install command for this repository (our install coverage is only about 4%). Check its README or releases page.
Who is it for?
We filed it under these tags: MCP 服务. The tags come from the entry itself, not a taxonomy we imposed.
Who maintains it?
repository aparajithn/agent-scraper-mcp;first catalogued 2026-10-09;last seen 2026-10-16。There is no official certification or quality rating here — we record sources and dates only.
**The #1 most requested utility for AI agents** — professional web scraping, screenshots, and content extraction via MCP + REST API. Features 🌐 **Clean Content Extraction** — Extract readable text/markdown from any webpage (like Readability) 🎯 **Structured Scraping** — Extract specific data using CSS selectors 📸 **Screenshots** — Capture full-page or viewport screenshots with Playwright 🔗 **Link Extraction** — Get all links from a page with optional regex filtering 📋 **Metadata Extraction** — Extract title, description, Open Graph tags, favicon, etc 🔍 **Google Search** — Search Google and get results programmatically Quick Start MCP Configuration Add to your MCP settings file (cline_mcp_settings.json or similar): REST API Base URL: https://agent-scraper-mcp.onrender.com Scrape URL (Clean Content) Response: Scrape Structured Data Response: Screenshot URL Response: Extract Links Extract Metadata Search Google Pricing Free Tier - **50 requests per IP per day** - All tools included - No credit card required Paid Tier (HTTP 402 / x402 Payment) After free tier exhausted: - **Scraping tools**: $0.005/request (scrape_url, scrape_structured, extract_links, extract_meta, search_google) - **Screenshot tool**: $0.01/request (higher due to compute cost) Payment via the x402 protocol (HTTP 402) in USDC on Base: - Wallet address (payTo): 0x8E844a7De89d7CfBFe9B4453E65935A22F146aBB When you exceed the free tier, the server responds with HTTP 402 carrying machine-readable payment requirements (x402 v1), so x402-aware clients pay and retry automatically: To pay manually, attach an X-Payment header containing a base64-encoded JSON envelope with an EIP-3009 TransferWithAuthorization (USDC on Base) signed with the payer's EIP-712 key for the exact price, addressed to the wallet above, with an unused nonce. Payments are verified cryptographically (signature recovery + amount/recipient/deadline/replay checks) before the request is served — applies to both the REST API and MCP tools/call. Collecting revenue (server operator) With X402_SETTLER_PRIVATE_KEY set, every verified payment is executed on-chain within seconds: the EIP-3009 transferWithAuthorization is submitted to the USDC contract on Base and the USDC moves from the payer to X402_WALLET_ADDRESS. The settler key does **not** need to be the receiving wallet's key — any address may execute the authorization, so a dedicated gas-only burner key can submit the transactions while funds land in the main wallet. It only needs a small ETH balance on Base for gas. Additional env vars: X402_RPC_URL (default https://mainnet.base.org) and X402_SETTLE_MIN_MICROUSD (default 0 — settle each payment immediately; raise it to batch small payments). Failed settlements are retried with backoff and, if all retries fail, the full authorization is written to the logs (CRITICAL) for manual redemption — no payment is silently lost. Tools Reference 1. scrape_url Extract clean, readable content from any webpage (like Readability). **Parameters:** - url (string, required): URL to scrape - format (string, optional): Output format — text, markdown, or html (default: markdown) **Returns:** {success, url, title, content, format}