crw
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 Tavily, 1.5x faster than Firecrawl in 1K-URL benchmarks. 6 MB RAM, single binary. Self-host or use ma
The crw MCP server delivers web scraping, crawling, and search functionality to AI agents through a unified Model Context Protocol interface. Built in Rust, it converts web pages into clean markdown or structured JSON while offering scrape, crawl, map, search, and extract operations. It serves as a Firecrawl-compatible alternative that can run locally as a lightweight binary or connect to a managed cloud API. Developers can integrate it with Claude Code, Cursor, Windsurf, and other MCP-compatible tools to give agents web data access.
Key Features
Use Cases
- 01Equipping AI coding assistants with real-time web search and documentation scraping
- 02Enabling agents to crawl technical documentation sites and convert them to markdown knowledge bases
- 03Extracting structured product data from e-commerce sites into JSON schemas for analysis
- 04Providing AI agents with up-to-date web search results during conversational workflows
- 05Mapping website sitemaps and URL structures without full page retrieval
- 06Replacing Firecrawl or Tavily in existing agent workflows with a faster, self-hostable solution
Related MCP Servers
View moremarkitdown
Python tool for converting files and office documents to Markdown.
firecrawl
The context API to search, scrape, and interact with the web at scale. 🔥
prompts.chat
f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.
langflow
Langflow is a powerful tool for building and deploying AI-powered agents and workflows.
crw — FAQ
What is the crw MCP server?+
The crw MCP server is a web scraping and search tool built in Rust that exposes five operations—scrape, crawl, map, search, and extract—to AI agents through the Model Context Protocol. It can run locally as a lightweight binary or connect to a managed cloud API.
How do I install the crw MCP server?+
Run 'curl -fsSL https://fastcrw.com/install | sh' to install the binary locally, or add your API key with 'curl -fsSL https://fastcrw.com/install | CRW_API_KEY=crw_live_... sh' to configure cloud mode. For MCP server registration only, use 'npx -y crw-mcp@latest install' to add it to detected AI tools.
Which AI clients work with the crw MCP server?+
The installer automatically detects and configures Claude Code, Cursor, Codex, Gemini CLI, OpenCode, and Windsurf. Manual MCP server setup is supported for any tool that implements the Model Context Protocol.
Do I need an API key to use crw?+
No API key is required for local mode—the binary runs entirely offline. To use the managed cloud API with proxies, JavaScript rendering, and search, create a free account for 1,000 credits without a credit card.
Is the crw MCP server free?+
The open-source binary is free under AGPL-3.0 and runs locally at no cost. The managed cloud API offers 1,000 free credits, then operates on a pay-per-use billing model.
What are the prerequisites for self-hosting crw?+
Self-hosting requires only the single Rust binary, which runs on macOS and Linux on Intel or ARM. Optional features like JavaScript rendering or web search require separate configuration of renderers and search providers.
How do I install crw?+
Open the source repository on GitHub and follow its README. crw is a mcp server — MCP Agents Market links you directly to the official repo.
Is crw free?+
crw is an open-source project hosted on GitHub. Check the repository for its license and any usage requirements.