Firecrawl CLI
The Firecrawl command-line client with agent skills: web search, scraping, crawling, URL mapping and page interaction
- 674 ★ on the repository
- Last commit
Extended access
Why this level
- Sends URLs and queries to an external service and spends credits
- Can change web access settings of agents
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add cli/firecrawl-cliDetects the agents on your machine, shows the access level and pins the version.
What it sends to the author: what it sends to the author: anonymous usage data during authentication — CLI version, OS, Node.js version, and detected development tools. no command data, URLs, or file contents are sent. To turn it off: FIRECRAWL_NO_TELEMETRY=1 in the server environment.
Other ways to install
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- Sends URLs and queries to an external service and spends credits
- Can change web access settings of agents
This is third-party code. Review the repository files before installing.
What it does
The CLI gives the agent web access through the Firecrawl service: search finds pages, scrape turns a page into markdown, map discovers URLs on a site, crawl pulls a whole section, interact clicks and fills forms, monitor watches for changes, and parse handles local PDF and DOCX files. There are dedicated indexes for research papers and developer sources: issues, pull requests and docs. firecrawl init installs the CLI, signs in and places skills into detected agents, and firecrawl setup mcp adds the Firecrawl MCP server to editors. Results are saved in the project's .firecrawl folder.
Who it is for. For developers and researchers who need an agent to read websites and gather sources online.
Good fit when
- The agent's built-in web search is not enough or cannot render JavaScript
- You need to export a whole documentation section to markdown
- You need scheduled monitoring of page changes
Not a fit when
- The agent's standard web fetch is enough
- URLs and queries must not be sent to a third-party cloud service
Example request
Find recent articles about WebGPU and save the three most useful ones as markdownLimitations
Works through the Firecrawl cloud API, requests use account credits, and there is a free tier. A self-hosted instance can be set with --api-url. setup defaults disables the agents' native web access and can be reverted with --undo. Availability from Russia without VPN is unverified.
How to disable. If you changed agent defaults, run firecrawl setup defaults --undo, then remove the firecrawl skills from agent directories and run npm uninstall -g firecrawl-cli.
FAQ
Can it run without the cloud?
Yes, with self-hosted Firecrawl via --api-url or FIRECRAWL_API_URL; no key is needed for a custom URL.
How do I install skills into one agent only?
Add --agent, for example firecrawl setup skills --agent codex.
Discussion
No questions or reviews yet.
Related
CLI toolsOfficial Firecrawl MCP server: web search, page scraping to Markdown, site crawling and in-page actions
A Rust server that turns pages into Markdown or JSON: search, scrape, site map, crawl and PDF through MCP, a CLI and a Firecrawl-compatible API
An open-source crawler that turns websites into clean Markdown for AI agents: install from PyPI, run in Docker and connect to Claude Code over MCP
A web research skill: SearXNG searches, Camofox reads pages and CloakBrowser opens sites that check their visitors
Local-first Rust tool for web extraction: scrape, crawl and structured data for LLMs, with a CLI, REST API and MCP server
A CLI and MCP server that lets an agent drive your real Chrome with its logged-in sessions: 103 commands across 36 platforms plus browser automation
Comparison with similar tools
Entries that share the main search query, and how they differ.
| Entry | Official | Repository stars | Main difference |
|---|---|---|---|
| Firecrawl CLI (this entry) | no | 674 | |
| Tavily Agent Skills | yes | 491 | eight Tavily skills built on the tvly CLI |
| NewsCrawler | no | 636 | the news-extractor skill pulls the title |
| jina-cli: web reading and search via Jina Reader | no | 311 | a skill and the jina CLI |
README in short
The README covers installing via npm or a single init command, the core, build and workflows skill groups, installing the MCP server and making Firecrawl the agents' default web provider. It explains sign-in options: browser, key, environment variable and self-hosted. A command reference for scrape, search, map, crawl, agent and others follows with examples.