firecrawl / firecrawl-claude-plugin
✓ Official★ 152A skill package that teaches your agent 6 capabilities — every one documented and browsable below, no GitHub required · by firecrawl.
Each skill below is one capability this package teaches your agent. Install the whole package, or open a skill to install just that one.
AI-powered autonomous extraction. The agent navigates sites and extracts structured data (takes 2-5 minutes).
1 file — installable on its own
Bulk extract content from a website. Crawls pages following links up to a depth/limit.
1 file — installable on its own
Experimental. Convenience command that combines map + scrape to save an entire site as local files.
1 file — installable on its own
Discover URLs on a site. Use --search to find a specific page within a large site.
1 file — installable on its own
Scrape one or more URLs. Returns clean, LLM-optimized markdown. Multiple URLs are scraped concurrently.
1 file — installable on its own
Web search with optional content scraping. Returns search results as JSON, optionally with full page content.
1 file — installable on its own
Firecrawl Plugin for Claude Code
Turn any website into clean, LLM-ready markdown or structured data — directly from Claude Code.
This plugin adds the Firecrawl CLI as a skill to Claude Code, giving it the ability to scrape, search, crawl, and map the web.
Features
- Search - Web search with optional scraping of results (supports web, news, and image sources)
- Scrape - Extract clean markdown content from any webpage, with JavaScript rendering
- Map - Discover all URLs on a website
- Crawl - Extract content from entire websites
- Browser - Launch cloud browser sessions and execute Playwright code remotely
All operations include automatic JavaScript rendering, anti-bot handling, and proxy rotation.
Installation
1. Install the Plugin
In Claude Code, run /plugin and search for firecrawl, then select it to install.
2. Install the Firecrawl CLI
The plugin requires the Firecrawl CLI to be installed globally:
npm install -g firecrawl-cli3. Authenticate
Run the following to authenticate via your browser:
firecrawl login --browserOr authenticate with an API key directly:
firecrawl login --api-key "fc-YOUR-API-KEY"You can also set the key as an environment variable (add to ~/.zshrc or ~/.bashrc for persistence):
export FIRECRAWL_API_KEY=fc-YOUR-API-KEYGet your free API key at: https://firecrawl.dev/app/api-keys
4. Verify Setup
firecrawl --statusYou should see your authentication status, concurrency limit, and remaining credits.
Usage
Once installed, Claude Code will automatically use Firecrawl for web tasks. Just ask naturally:
Search the web:
Search for "best practices for React testing" and compile the key recommendationsScrape a page:
Scrape https://docs.firecrawl.dev/introduction and summarize the key pointsDiscover site structure:
Map all URLs on https://firecrawl.devResearch a topic:
Research the latest developments in AI agents and give me a summaryCLI Commands
The plugin uses these Firecrawl CLI commands under the hood:
| Command | Description |
|---|---|
firecrawl search "query" | Search the web (supports --sources, --scrape, --tbs for time filters) |
firecrawl scrape <url> | Scrape a single page to markdown |
firecrawl map <url> | Discover all URLs on a site |
firecrawl browser launch/execute/list/close | Manage cloud browser sessions and execute Playwright code |
firecrawl --status | Check auth status, concurrency, and credits |
Output Files
Results are saved to a .firecrawl/ directory in your project to keep Claude Code's context window clean:
.firecrawl/search-react_server_components.json
.firecrawl/docs.github.com-actions-overview.md
.firecrawl/firecrawl.dev.mdConfiguration
| Variable | Required | Description |
|---|---|---|
FIRECRAWL_API_KEY | Yes (if not using firecrawl login) | Your Firecrawl API key |
FIRECRAWL_API_URL | No | Custom API endpoint (for self-hosted instances) |
Self-Hosted Deployment
Firecrawl can be self-hosted. Set FIRECRAWL_API_URL to point to your instance:
export FIRECRAWL_API_URL=https://your-firecrawl-instance.comSee the Firecrawl documentation for self-hosting instructions.
Resources
License
This plugin is licensed under AGPL-3.0, consistent with Firecrawl's open-source license.
Support
Install the whole package (6 skills):
npx skills add https://github.com/firecrawl/firecrawl-claude-pluginOr install a single skill:
npx skills add https://github.com/firecrawl/firecrawl-claude-plugin --skill <name>Pick the skill name from the Skills tab — each entry there installs independently.