Directory
Firecrawl
Web extraction API + MCP server
Free tier + paidAgent tools & orchestrationgithub.com
What it is
Turns arbitrary sites into LLM-ready markdown or schema-constrained JSON, handling JS rendering, crawling and cleanup. Scrape, crawl, map, batch, search-with-full-content, browser interaction and autonomous agent modes. Parses web-hosted PDFs and DOCX. Self-hostable (AGPL core). ~128k stars.
Why it earns a slot
The archive-migration tool. Point it at an existing site and get every back-issue article as clean structured JSON ready for Supabase. Also the competitive-research tool — crawl other publications and extract their section taxonomy. Free tier is 1,000 credits; a typical archive fits inside $16/mo.
Getting started
npx -y firecrawl-cli@latest init --all
Neighbourhood
How Firecrawl sits against the rest of the atlas — swaps, companions and the tools builders actually save alongside it.
Also in Agent tools & orchestration
playwright-mcp
github.comNot yet swept
Browser automation MCP (Microsoft)
FreeAgent tools & orchestration
Free
Open dossier
awesome-mcp-servers
github.comNot yet swept
MCP directory (~50 categories)
FreeAgent tools & orchestration
Free
Open dossier
cc-switch
github.comNot yet swept
Desktop config manager for AI CLIs
FreeAgent tools & orchestration
Free · MIT
Open dossier
claude-code-router
github.comNot yet swept
Local model routing proxy
FreeAgent tools & orchestration
Free · MIT
Open dossier