Index live · v1.10.0 · NOV 22 2026

AgenticSkills is reader-supported. When you buy through links on our site, we may earn an affiliate commission. How that works.

Firecrawl

Turns any website into clean Markdown or structured data an agent can use — scrape, crawl and search.

Also available as an MCP server

This page covers Firecrawl the product. To let an agent talk to it over the Model Context Protocol, see the Firecrawl MCP server.

Overview

Firecrawl is a web data API for agents: give it a URL or a query and it returns the page as clean Markdown or structured JSON, with JavaScript rendering and anti-bot handling done on its side. Crawl and map cover whole sites, search returns pages rather than links, and interact drives pages that need clicks first. The core is open source and self-hostable; the hosted API is what the official skill and MCP server call.

Why it's indexed

The web as agent input, not HTML soup — and the engine behind both a listed skill and a listed MCP server, so one key covers the terminal and the conversation.

Editorial judgment, not a measurement — see our methodology. Listing is never paid for; the website link above is an affiliate link, disclosed at /disclosures. The relationship never decides whether a tool is listed.

At a glance

Vendor
Firecrawl
License
AGPL-3.0
Deployment
Hybrid
Languages
Python, TypeScript, Go, Rust
Pricing model
Open source · Free tier · Usage-based · Subscription · Enterprise

Pricing is shown as a model, not a rate. Published rates change without notice — check the vendor's own page before budgeting.

Tags

scrapingcrawlingmarkdownweb-data

Also in Web Data & Browsing

Newsletter

Stay ahead of the AI skills curve

Every issue: what we added to the directory, what we rejected and why, and one workflow worth stealing. Nothing you'd get from an AI news roundup.

Free forever. Unsubscribe anytime. No spam. Read a past issue.