Flagged: sudo usage. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by us · MCP Server · ★ 976
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is crw safe to install? View the security audit →
fastCRW Self-hosted, Rust-native web crawler & scraper for AI agents The open-source alternative to Firecrawl. One static binary, 50 MB RAM idle, Firecrawl-compatible REST API on both and (scrape, crawl, map, search, extract, plus v2 batch & parse) — a drop-in for the official Firecrawl SDKs — plus first-class MCP. Self-host free under AGPL-3.0, or hit our managed API at . Reproducible 63.74% truth-recall on the public 1,000-URL dataset (, 2026-05-08) — see fastcrw.com/benchmarks. Built in Rust because every millisecond of agent latency compounds. <p a
| Stars | 976 |
| Forks | 74 |
| Language | Rust |
| Category | MCP Server |
| License | AGPL-3.0 |
| Quality Score | 66.9696684515314/100 |
| Open Issues | 2 |
| Last Updated | 2026-09-12 |
| Created | 2026-03-02 |
| Platforms | browser, docker, mcp, rust |
| Est. Tokens | ~27k |
Looking for a crw alternative? If you're comparing crw with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Fast, local-first web content extraction for LLMs. Scrape, crawl, extract structured data — all from Rust. CLI
Self-hosted URL- and file-to-Markdown service for humans and AI agents - web pages, documents, images, audio,
A powerful Model Context Protocol (MCP) server that provides an all-in-one solution for public web access.
Flow-Like: Strongly Typed Enterprise Scale Workflows. Built for scalability, speed, seamless AI integration an
Stop configuring your AI stack. Start using it. One command brings a complete pre-wired LLM stack with hundred
Best headless browser for AI agents. Lite, Fast, High-Compatibility. Built in Rust
Explore other popular mcp server tools:
crw is Fast, lightweight Firecrawl/Tavily alternative in Rust. Web scraper, crawler & search API with MCP server for AI agents. Drop-in Firecrawl-compatible API (/scrape, /crawl, /search). 2.3x faster than T. It is categorized as a MCP Server with 976 GitHub stars.
crw is primarily written in Rust. It covers topics such as ai, ai-agents, crawler.
You can find installation instructions and usage details in the crw GitHub repository at github.com/us/crw. The project has 976 stars and 74 forks, indicating an active community.
crw is released under the AGPL-3.0 license, making it free to use and modify according to the license terms.
The top alternatives to crw on Agent Skills Hub include webclaw, pullmd, brightdata-mcp. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: