CRW
Lightweight web scraper and crawler built in Rust, designed as a Firecrawl alternative for AI agents.
High-performance web scraping and crawling tool that outputs markdown, HTML, plain text, or JSON. Supports single-page application rendering, CSS selectors, XPath extraction, and LLM-powered structured data extraction using JSON schemas. Runs as a single binary with minimal resource usage (6.6 MB idle RAM) and includes SSRF protection, rate limiting, and robots.txt compliance. Available via npm (crw-mcp), Cargo, Docker, or direct binary download.
Source
Repository: https://github.com/us/crw
Maintain CRW?
Let people know it's listed here — add the badge (live metrics, light/dark aware) or a plain link to your README or docs.
[](https://getagentictools.com/mcp/us-crw?ref=badge) Related mcp
Anytype Official MCP server for Anytype, the encrypted local-first knowledge platform, enabling search, space and member management, and c
AppleScript Enables AI to execute AppleScript code on macOS systems, providing access to applications and system features like Notes, Calendar
Kagi Search Integrates Kagi's advanced search capabilities into workflows, enabling high-quality, privacy-focused web information retrieval fo
Stata Integrates Stata statistical software with code editors like VS Code and Cursor, enabling direct command execution, real-time outp
Second Brain Self-hosted semantic memory MCP server on Cloudflare Workers with vector embeddings for intelligent recall and 4 tools for persona
Docfork Retrieves up-to-date documentation and code examples for any software library through the Docfork API, automatically selecting rel