Open-source web scraper for AI agents with scrape, crawl, and map tools
The io.github.fastcrw/crw MCP server is an open-source web scraper for AI agents. It provides tools that support scrape, crawl, and map operations, enabling agent-driven retrieval and traversal of web content for downstream processing.
🛠️ Key Features
Open-source web scraper
Tools for scrape
Tools for crawl
Tools for map
🚀 Use Cases
Scraping web content for AI agents
Crawling through linked pages or resources
Mapping web content or relationships based on retrieved data
⚡ Developer Benefits
Agent-oriented toolset for web interaction
Separate capabilities aligned to scraping, crawling, and mapping
⚠️ Limitations
Available details are limited to the server description and do not specify scope, supported sites, rate limits, or configuration options.
Runs local and free, no account needed. To use the Cloud, paste your key into
the same command and it installs the binary, connects the key, and registers the
MCP server with the AI coding tools you already have:
bash
curl -fsSL https://fastcrw.com/install | CRW_API_KEY=crw_live_... sh
bash
crw search "rust tutorials"
Claude Code, Cursor, Codex, Gemini CLI, OpenCode and Windsurf are picked up
automatically when they are already set up; nothing else is touched, and your
key stays in ~/.config/crw/config.toml rather than being copied into each
tool. Add CRW_NO_AGENTS=1 to skip that step, or run crw setup on its own to
choose interactively.
1000 free credits, no credit card. Managed proxies, JS rendering and search,
with nothing to run or keep up to date.
Get my free key →
On Firecrawl's own public 1,000-URL dataset, fastCRW recovered more truth than
Crawl4AI and Firecrawl, matched the fastest median latency, and idled at
~14 MB RAM.
On a different benchmark entirely, answer accuracy rather than scrape recall,
fastCRW answers 90.0% of the 600 AA-Omniscience questions correctly. Every
product listed on the Artificial Analysis Search Index sits below it.