Skip to main content

​
Installation

Install the Firecrawl CLI globally using npm:
CLI
# Install globally with npm
npm install -g firecrawl-cli
If you are using any AI agent like Claude Code, you can install the Firecrawl skill below and the agent will be able to set it up for you. 
npx skills add firecrawl/cli
After installing the skill, restart Claude Code for it to discover the new skill.

​
Authentication

Before using the CLI, you need to authenticate with your Firecrawl API key.

​
Login

CLI
# Interactive login (opens browser or prompts for API key)
firecrawl login

# Login with browser authentication (recommended for agents)
firecrawl login --browser

# Login with API key directly
firecrawl login --api-key fc-YOUR-API-KEY

# Or set via environment variable
export FIRECRAWL_API_KEY=fc-YOUR-API-KEY

​
View Configuration

CLI
# View current configuration and authentication status
firecrawl view-config

​
Logout

CLI
# Clear stored credentials
firecrawl logout

​
Self-Hosted / Local Development

For self-hosted Firecrawl instances or local development, use the --api-url option:
CLI
# Use a local Firecrawl instance (no API key required)
firecrawl --api-url http://localhost:3002 scrape https://example.com

# Or set via environment variable
export FIRECRAWL_API_URL=http://localhost:3002
firecrawl scrape https://example.com

# Configure and persist the custom API URL
firecrawl config --api-url http://localhost:3002
When using a custom API URL (anything other than https://api.firecrawl.dev), API key authentication is automatically skipped, allowing you to use local instances without an API key.

​
Check Status

Verify installation, authentication, and view rate limits:
CLI
firecrawl --status
Output when ready: 
  🔥 firecrawl cli v1.1.1

  ● Authenticated via FIRECRAWL_API_KEY
  Concurrency: 0/100 jobs (parallel scrape limit)
  Credits: 500,000 remaining
  • Concurrency: Maximum parallel jobs. Run parallel operations close to this limit but not above.
  • Credits: Remaining API credits. Each scrape/crawl consumes credits.

​
Commands

​
Scrape

Scrape a single URL and extract its content in various formats.
Use --only-main-content to get clean output without navigation, footers, and ads. This is recommended for most use cases where you want just the article or main page content.
CLI
# Scrape a URL (default: markdown output)
firecrawl https://example.com

# Or use the explicit scrape command
firecrawl scrape https://example.com

# Recommended: use --only-main-content for clean output without nav/footer
firecrawl https://example.com --only-main-content

​
Output Formats

CLI
# Get HTML output
firecrawl https://example.com --html

# Multiple formats (returns JSON)
firecrawl https://example.com --format markdown,links

# Get images from a page
firecrawl https://example.com --format images

# Get a summary of the page content
firecrawl https://example.com --format summary

# Track changes on a page
firecrawl https://example.com --format changeTracking

# Available formats: markdown, html, rawHtml, links, screenshot, json, images, summary, changeTracking, attributes, branding

​
Scrape Options

CLI
# Extract only main content (removes navs, footers)
firecrawl https://example.com --only-main-content

# Wait for JavaScript rendering
firecrawl https://example.com --wait-for 3000

# Take a screenshot
firecrawl https://example.com --screenshot

# Include/exclude specific HTML tags
firecrawl https://example.com --include-tags article,main
firecrawl https://example.com --exclude-tags nav,footer

# Save output to file
firecrawl https://example.com -o output.md

# Pretty print JSON output
firecrawl https://example.com --format markdown,links --pretty

# Force JSON output even with single format
firecrawl https://example.com --json

# Show request timing information
firecrawl https://example.com --timing
Available Options:
OptionShortDescription
--url <url>-uURL to scrape (alternative to positional argument)
--format <formats>-fOutput formats (comma-separated): markdown, html, rawHtml, links, screenshot, json, images, summary, changeTracking, attributes, branding
--html-HShortcut for --format html
--only-main-contentExtract only main content
--wait-for <ms>Wait time in milliseconds for JS rendering
--screenshotTake a screenshot
--include-tags <tags>HTML tags to include (comma-separated)
--exclude-tags <tags>HTML tags to exclude (comma-separated)
--output <path>-oSave output to file
--jsonForce JSON output even with single format
--prettyPretty print JSON output
--timingShow request timing and other useful information
Search the web and optionally scrape the results.
CLI
# Search the web
firecrawl search "web scraping tutorials"

# Limit results
firecrawl search "AI news" --limit 10

# Pretty print results
firecrawl search "machine learning" --pretty

​
Search Options

CLI
# Search specific sources
firecrawl search "AI" --sources web,news,images

# Search with category filters
firecrawl search "react hooks" --categories github
firecrawl search "machine learning" --categories research,pdf

# Time-based filtering
firecrawl search "tech news" --tbs qdr:h   # Last hour
firecrawl search "tech news" --tbs qdr:d   # Last day
firecrawl search "tech news" --tbs qdr:w   # Last week
firecrawl search "tech news" --tbs qdr:m   # Last month
firecrawl search "tech news" --tbs qdr:y   # Last year

# Location-based search
firecrawl search "restaurants" --location "Berlin,Germany" --country DE

# Search and scrape results
firecrawl search "documentation" --scrape --scrape-formats markdown

# Save to file
firecrawl search "firecrawl" --pretty -o results.json
Available Options:
OptionDescription
--limit <number>Maximum results (default: 5, max: 100)
--sources <sources>Sources to search: web, images, news (comma-separated)
--categories <categories>Filter by category: github, research, pdf (comma-separated)
--tbs <value>Time filter: qdr:h (hour), qdr:d (day), qdr:w (week), qdr:m (month), qdr:y (year)
--location <location>Geo-targeting (e.g., “Berlin,Germany”)
--country <code>ISO country code (default: US)
--timeout <ms>Timeout in milliseconds (default: 60000)
--ignore-invalid-urlsExclude URLs invalid for other Firecrawl endpoints
--scrapeScrape search results
--scrape-formats <formats>Formats for scraped content (default: markdown)
--only-main-contentInclude only main content when scraping (default: true)
--jsonOutput as JSON
--output <path>Save output to file
--prettyPretty print JSON output

​
Map

Discover all URLs on a website quickly.
CLI
# Discover all URLs on a website
firecrawl map https://example.com

# Output as JSON
firecrawl map https://example.com --json

# Limit number of URLs
firecrawl map https://example.com --limit 500

​
Map Options

CLI
# Filter URLs by search query
firecrawl map https://example.com --search "blog"

# Include subdomains
firecrawl map https://example.com --include-subdomains

# Control sitemap usage
firecrawl map https://example.com --sitemap include   # Use sitemap
firecrawl map https://example.com --sitemap skip      # Skip sitemap
firecrawl map https://example.com --sitemap only      # Only use sitemap

# Ignore query parameters (dedupe URLs)
firecrawl map https://example.com --ignore-query-parameters

# Wait for map to complete with timeout
firecrawl map https://example.com --wait --timeout 60

# Save to file
firecrawl map https://example.com -o urls.txt
firecrawl map https://example.com --json --pretty -o urls.json
Available Options:
OptionDescription
--url <url>URL to map (alternative to positional argument)
--limit <number>Maximum URLs to discover
--search <query>Filter URLs by search query
--sitemap <mode>Sitemap handling: include, skip, only
--include-subdomainsInclude subdomains
--ignore-query-parametersTreat URLs with different params as same
--waitWait for map to complete
--timeout <seconds>Timeout in seconds
--jsonOutput as JSON
--output <path>Save output to file
--prettyPretty print JSON output

​
Crawl

Crawl an entire website starting from a URL.
CLI
# Start a crawl (returns job ID immediately)
firecrawl crawl https://example.com

# Wait for crawl to complete
firecrawl crawl https://example.com --wait

# Wait with progress indicator
firecrawl crawl https://example.com --wait --progress

​
Check Crawl Status

CLI
# Check crawl status using job ID
firecrawl crawl <job-id>

# Example with a real job ID
firecrawl crawl 550e8400-e29b-41d4-a716-446655440000

​
Crawl Options

CLI
# Limit crawl depth and pages
firecrawl crawl https://example.com --limit 100 --max-depth 3 --wait

# Include only specific paths
firecrawl crawl https://example.com --include-paths /blog,/docs --wait

# Exclude specific paths
firecrawl crawl https://example.com --exclude-paths /admin,/login --wait

# Include subdomains
firecrawl crawl https://example.com --allow-subdomains --wait

# Crawl entire domain
firecrawl crawl https://example.com --crawl-entire-domain --wait

# Rate limiting
firecrawl crawl https://example.com --delay 1000 --max-concurrency 2 --wait

# Custom polling interval and timeout
firecrawl crawl https://example.com --wait --poll-interval 10 --timeout 300

# Save results to file
firecrawl crawl https://example.com --wait --pretty -o results.json
Available Options:
OptionDescription
--url <url>URL to crawl (alternative to positional argument)
--waitWait for crawl to complete
--progressShow progress indicator while waiting
--poll-interval <seconds>Polling interval (default: 5)
--timeout <seconds>Timeout when waiting
--statusCheck status of existing crawl job
--limit <number>Maximum pages to crawl
--max-depth <number>Maximum crawl depth
--include-paths <paths>Paths to include (comma-separated)
--exclude-paths <paths>Paths to exclude (comma-separated)
--sitemap <mode>Sitemap handling: include, skip, only
--allow-subdomainsInclude subdomains
--allow-external-linksFollow external links
--crawl-entire-domainCrawl entire domain
--ignore-query-parametersTreat URLs with different params as same
--delay <ms>Delay between requests
--max-concurrency <n>Maximum concurrent requests
--output <path>Save output to file
--prettyPretty print JSON output

​
Agent

Search and gather data from the web using natural language prompts.
CLI
# Basic usage - URLs are optional
firecrawl agent "Find the top 5 AI startups and their funding amounts" --wait

# Focus on specific URLs
firecrawl agent "Compare pricing plans" --urls https://slack.com/pricing,https://teams.microsoft.com/pricing --wait

# Use a schema for structured output
firecrawl agent "Get company information" --urls https://example.com --schema '{"name": "string", "founded": "number"}' --wait

# Use schema from a file
firecrawl agent "Get product details" --urls https://example.com --schema-file schema.json --wait

​
Agent Options

CLI
# Use Spark 1 Pro for higher accuracy
firecrawl agent "Competitive analysis across multiple domains" --model spark-1-pro --wait

# Set max credits to limit costs
firecrawl agent "Gather contact information from company websites" --max-credits 100 --wait

# Check status of an existing job
firecrawl agent <job-id> --status

# Custom polling interval and timeout
firecrawl agent "Summarize recent blog posts" --wait --poll-interval 10 --timeout 300

# Save output to file
firecrawl agent "Find pricing information" --urls https://example.com --wait -o pricing.json --pretty
Available Options:
OptionDescription
--urls <urls>Optional list of URLs to focus the agent on (comma-separated)
--model <model>Model to use: spark-1-mini (default, 60% cheaper) or spark-1-pro (higher accuracy)
--schema <json>JSON schema for structured output (inline JSON string)
--schema-file <path>Path to JSON schema file for structured output
--max-credits <number>Maximum credits to spend (job fails if limit reached)
--statusCheck status of existing agent job
--waitWait for agent to complete before returning results
--poll-interval <seconds>Polling interval when waiting (default: 5)
--timeout <seconds>Timeout when waiting (default: no timeout)
--output <path>Save output to file
--jsonOutput as JSON format
--prettyPretty print JSON output

​
Credit Usage

Check your team’s credit balance and usage.
CLI
# View credit usage
firecrawl credit-usage

# Output as JSON
firecrawl credit-usage --json --pretty

​
Version

Display the CLI version.
CLI
firecrawl version
# or
firecrawl --version

​
Global Options

These options are available for all commands:
OptionShortDescription
--statusShow version, auth, concurrency, and credits
--api-key <key>-kOverride stored API key for this command
--api-url <url>Use custom API URL (for self-hosted/local development)
--help-hShow help for a command
--version-VShow CLI version

​
Output Handling

The CLI outputs to stdout by default, making it easy to pipe or redirect:
CLI
# Pipe markdown to another command
firecrawl https://example.com | head -50

# Redirect to a file
firecrawl https://example.com > output.md

# Save JSON with pretty formatting
firecrawl https://example.com --format markdown,links --pretty -o data.json

​
Format Behavior

  • Single format: Outputs raw content (markdown text, HTML, etc.)
  • Multiple formats: Outputs JSON with all requested data
CLI
# Raw markdown output
firecrawl https://example.com --format markdown

# JSON output with multiple formats
firecrawl https://example.com --format markdown,links

​
Examples

​
Quick Scrape

CLI
# Get markdown content from a URL (use --only-main-content for clean output)
firecrawl https://docs.firecrawl.dev --only-main-content

# Get HTML content
firecrawl https://example.com --html -o page.html

​
Full Site Crawl

CLI
# Crawl a docs site with limits
firecrawl crawl https://docs.example.com --limit 50 --max-depth 2 --wait --progress -o docs.json

​
Site Discovery

CLI
# Find all blog posts
firecrawl map https://example.com --search "blog" -o blog-urls.txt

​
Research Workflow

CLI
# Search and scrape results for research
firecrawl search "machine learning best practices 2024" --scrape --scrape-formats markdown --pretty

​
Agent

CLI
# URLs are optional
firecrawl agent "Find the top 5 AI startups and their funding amounts" --wait

# Focus on specific URLs
firecrawl agent "Compare pricing plans" --urls https://slack.com/pricing,https://teams.microsoft.com/pricing --wait

​
Combine with Other Tools

CLI
# Extract URLs from search results
jq -r '.data.web[].url' search-results.json

# Get titles from search results
jq -r '.data.web[] | "\(.title): \(.url)"' search-results.json

# Extract links and process with jq
firecrawl https://example.com --format links | jq '.links[].url'

# Count URLs from map
firecrawl map https://example.com | wc -l

​
Telemetry

The CLI collects anonymous usage data during authentication to help improve the product:
  • CLI version, OS, and Node.js version
  • Development tool detection (e.g., Cursor, VS Code, Claude Code)
No command data, URLs, or file contents are collected via the CLI. To disable telemetry, set the environment variable:
CLI
export FIRECRAWL_NO_TELEMETRY=1

​
Open Source

The Firecrawl CLI and Skill are open source and available on GitHub: firecrawl/cli