crw

Lightweight web scraping, crawling, and search API with MCP server support.

MCPResearchOpen source

Type: MCP
Transport: http
Open source: Yes
GitHub Stars: ★ 1.0k
Source: mcp-github
Repository: github.com/us/crw

Overview

crw is a fast, lightweight alternative to Firecrawl/Tavily, written in Rust. It provides an MCP server enabling AI agents to perform web scraping, crawling, and searching. Compatible with Firecrawl API (/scrape, /crawl, /search), it is 2.3x faster than Tavily and 1.5x faster than Firecrawl on a 1K-URL benchmark, with only 6MB memory usage. It can be self-hosted or used via managed cloud services. Ideal for AI applications requiring efficient handling of web data.

Capabilities

▪Web scraping
▪Website crawling
▪Online search
▪Structured JSON output
▪Markdown format output

Use cases

Automated content scrapingLarge-scale website crawlingReal-time online searchData extraction and analysis

Setup

Requires: API Key

curl -fsSL https://fastcrw.com/install | sh

This information was compiled by AI from public sources and may contain inaccuracies — please refer to the source.

FAQ

How to install crw?

Run the command: curl -fsSL https://fastcrw.com/install | sh

Do I need an API key?

Yes, an API key is required to use the managed cloud service.

Related skills

Scrapling

An adaptive web scraping framework capable of handling everything from single requests to large-scale scraping.

MCP

TrendRadar

An AI-driven tool for sentiment monitoring and trend analysis, supporting multi-platform aggregation, RSS subscription, and intelligent notifications.

MCP