aparajithn/agent-scraper-mcp

Verified

Summary

Web scraping MCP server for AI agents. 6 tools: clean content extraction, structured scraping with CSS selectors, full page screenshots via Playwright, link extraction, metadata extraction (OG/Twitter cards), and Google search. Free tier with x402 micropayments.

Links

Repository

Safety: Local MCP servers can run code and access files on your machine depending on how you configure them. Remote servers may send data to third-party services and require credentials. Review the repository and requested permissions before installing.

Install instructions

Add to Cursor

Where to put this

Merge into the existing file if needed. Top-level key: mcpServers.

Global

Linux / macOS~/.cursor/mcp.json

Windows%USERPROFILE%\.cursor\mcp.json

Project

Linux / macOS<project_folder>/.cursor/mcp.json

Windows<project_folder>\.cursor\mcp.json

{
  "mcpServers": {
    "aparajithn-agent-scraper-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "agent-scraper-mcp"
      ]
    }
  }
}

Replace placeholder values with secrets from your environment. Confirm the package name in the repository README; the catalog uses a best-guess npx -y target when registry metadata is not available.

Transport

stdio

Metadata

Primary category: Automation & Productivity
Popularity (composite): 85.0 / 100
GitHub stars: 1
Tags: Browser AutomationAutomation & Productivitywebscrapingmcpserverforagents.toolsclean