What it does
Firecrawl gives an assistant reliable web reading. It can run a web search and return results with page content, convert any URL or PDF into clean Markdown, map a site's URLs, crawl many pages with limits you set, click and type on pages that need interaction, and monitor a page for changes.
The hosted server has a free, rate-limited tier without an API key for scraping, search and parsing; the other tools need a Firecrawl account and use credits. You can also run it locally with npx or Docker, or point it at a self-hosted Firecrawl.
Limitations and requirements
Crawling, agent jobs and monitoring use Firecrawl credits on your account, so set limits on crawls. Keep the API key in your client's configuration or a secret manager, never in the server URL or a chat. Respect the terms and robots rules of the sites you read; scraped pages can contain instructions aimed at the model, so review results before acting on them.
Safety
Our team reviewed what this resource runs and the permissions it needs before publishing. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.
- Runs code or changes an assistant's behaviour
Sources
- Awesome MCP Servers first seen 13 Nov 2026 · last seen 17 Nov 2026 · its page on the source
Preview card provided by GitHub