StackMCP

Web Scraping Stack for Cursor

Intermediate5 servers29.4K tokens

Configuration

{
  "mcpServers": {
    "firecrawl-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "firecrawl-mcp"
      ],
      "env": {
        "FIRECRAWL_API_KEY": "YOUR_FIRECRAWL_API_KEY"
      }
    },
    "browserbase-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@browserbasehq/mcp-server-browserbase"
      ],
      "env": {
        "BROWSERBASE_API_KEY": "YOUR_BROWSERBASE_API_KEY",
        "BROWSERBASE_PROJECT_ID": "YOUR_BROWSERBASE_PROJECT_ID"
      }
    },
    "playwright-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@playwright/mcp"
      ]
    },
    "puppeteer-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-puppeteer"
      ]
    },
    "filesystem-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-filesystem",
        "/path/to/allowed/directory"
      ]
    }
  }
}

Where to save

Paste the config above into:

.cursor/mcp.json

Environment Variables

Replace the YOUR_ placeholders with your actual values.

FIRECRAWL_API_KEYrequired

Firecrawl API key

Used by: Firecrawl MCP

BROWSERBASE_API_KEYrequired

BrowserBase API key for authentication

Used by: BrowserBase MCP

BROWSERBASE_PROJECT_IDrequired

BrowserBase project identifier

Used by: BrowserBase MCP

What’s in this stack

Firecrawl MCP6 tools

Scrape and crawl websites, extract structured data, and perform batch web scraping with LLM-powered content analysis.

Crawl entire websites and extract clean, structured content from any page — handles JavaScript rendering and pagination automatically.

BrowserBase MCP12 tools

Automate cloud browsers with BrowserBase and Stagehand to navigate pages, extract content, take screenshots, and interact with web elements.

Run headless browsers in the cloud with built-in anti-detection, proxy rotation, and CAPTCHA solving for scraping at scale.

Playwright MCP20 tools

Automate browser interactions, take screenshots, fill forms, and test web applications using Microsoft Playwright from your AI editor.

Automate complex browser interactions like login flows, infinite scrolling, and multi-step navigation to reach deeply nested content.

Puppeteer MCP8 tools

Automate browsers with Puppeteer. Navigate pages, take screenshots, fill forms, and generate PDFs from your AI editor.

Control Chromium directly for fine-grained scraping tasks like screenshot capture, PDF generation, and dynamic page interaction.

Filesystem MCP11 tools

Read, write, search, and manage files on your local filesystem with secure directory-scoped access for your AI editor.

Save scraped data as JSON, CSV, or structured files locally — the final step in any data extraction pipeline.

Other editors

Claude CodeVS CodeWindsurfClaude DesktopContinue