AI Plugin Index
CRW Web Scraper
CommunityMCP server by us · updated · ★ 1.2k
Open-source web scraper for AI agents with scrape, crawl, and map tools CRW Web Scraper is a community project by us, not verified by a company domain.
Last commit 4 days ago
AGPL-3.0: copyleft, check the terms before using it in a product
Clear description, published package or server URL, 1,159 stars, original repository
Downloads a script from the internet and runs it
Install CRW Web Scraper
Built from the published package, never by AIclaude mcp add crw-web-scraper -- docker run -i --rm ghcr.io/us/crw:latestRun in your terminal. Add --scope user to use it in every project.
{
"mcpServers": {
"crw-web-scraper": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/us/crw:latest"
]
}
}
}Settings, Developer, Edit config. Paste into claude_desktop_config.json and restart.
{
"mcpServers": {
"crw-web-scraper": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/us/crw:latest"
]
}
}
}Add to ~/.cursor/mcp.json (all projects) or .cursor/mcp.json (this project).
{
"servers": {
"crw-web-scraper": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/us/crw:latest"
]
}
}
}Add to .vscode/mcp.json. VS Code uses "servers", not "mcpServers".
codex mcp add crw-web-scraper -- docker run -i --rm ghcr.io/us/crw:latest{
"mcpServers": {
"crw-web-scraper": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/us/crw:latest"
]
}
}
}Add to ~/.gemini/config/mcp_config.json (all projects) or .agents/mcp_config.json (this project).
gemini mcp add crw-web-scraper docker run -i --rm ghcr.io/us/crw:latestGemini CLI was replaced by Antigravity CLI in June 2026 and remains only for enterprise licences and paid API keys.
MCP servers run with your permissions and can read what you give them access to. Some need an API key: check the README and add it under env in the crw-web-scraper block.
Security check
C- Downloads a script from the internet and runs itIn
README.md:curl -fsSL https://fastcrw.com/install | sh
Checked automatically: README.md. This looks for known risky patterns and is not a full audit. How grades work
Alternatives to CRW Web Scraper
All alternatives →
Browser agents and stealth cloud browsers for AI: run web tasks, fill forms, extract data.
Let your AI agent operate any website through a real, logged-in browser session.
Dark web OSINT over Tor: search onion engines, scrape pages, report with your own model.
Web scraping with stealth HTTP, real browsers, and Cloudflare bypass. CSS selectors supported.
draw.io diagrams your AI agent draws on a live browser canvas that you can also edit by hand
AI browser agent: browses, clicks, types, and reads real web pages from plain-English instructions.
CRW Web Scraper: common questions
How do I install CRW Web Scraper?
In Claude Code run claude mcp add crw-web-scraper -- docker run -i --rm ghcr.io/us/crw:latest. For Claude Desktop, Cursor and VS Code, paste the config shown above and restart. See the install guides.
Is CRW Web Scraper the official server?
CRW Web Scraper is a community project by us, not verified by a company domain.
Is CRW Web Scraper free?
The code is published under the AGPL-3.0 licence. The service it connects to may have its own pricing.
Is CRW Web Scraper safe to use?
It scores 86 of 100. Grades: maintenance A, licence C, quality A. Security check: grade C (downloads a script from the internet and runs it). Review the code before you install. How grades work.
What are alternatives to CRW Web Scraper?
Similar MCP servers: browser-use, Actionbook, Robin: AI-Powered Dark Web OSINT, Scrapling MCP Server.
Does CRW Web Scraper work with ChatGPT?
Not directly. It runs locally, and ChatGPT only connects to remote servers with a URL. Use it in Claude Code, Claude Desktop, Cursor, VS Code or Codex.