Firecrawl MCP server

Read from the package source without running it. The installed server may list more.

• cancel_batch_scrapewrite action

  Cancels an active batch scraping job by its ID. The job will stop processing immediately and any pending tasks will be abandoned.

• cancel_crawlwrite action

  Cancel an active or pending crawl job by its ID. Once cancelled, the crawl will stop processing and cannot be resumed.

• crawl_urls
• crawl_urls_map

  Crawl and map multiple URLs from a website based on specified options. Discovers all accessible links starting from a base URL, with optional filtering by search query, sitemap, subdomains, and result limits.

• extract_structured_data

  Extract structured data from web pages using LLM analysis. Optionally augment extraction with web search, subdomain scanning, and source attribution.

• generate_llms_txt

  Generate an LLMs.txt file for a website to improve AI model discoverability and interaction. This operation crawls the specified URL and extracts relevant content to create a standardized LLMs.txt file.

• get_batch_scrape_status

  Retrieve the current status and progress of a batch scraping job. Use this to monitor ongoing or completed scrape operations.

• get_crawl_status

  Retrieve the current status and progress of a crawl job by its unique identifier. Use this to monitor ongoing or completed web crawling operations.

• get_deep_research_status

  Retrieve the current status and results of a deep research job. Use this to check progress and access findings from an ongoing or completed research task.

• get_extraction_status

  Retrieve the current status of a data extraction job using its unique identifier. Returns the job's progress, completion state, and any relevant metadata.

• get_llms_txt_generation_status

  Retrieve the current status and results of an LLMs.txt generation job. Use this to check if a generation job has completed and access the generated content.

• get_team_credit_usage

  Retrieve the remaining credit balance for the authenticated team. This shows how many credits are available for use.

• get_token_usage

  Retrieve the remaining token balance for the authenticated team's Extract operations. Returns current token usage information for the team.

• initiate_deep_research

  Initiates a comprehensive research process that iteratively analyzes multiple sources to deeply investigate a query. Returns structured findings formatted according to specified analysis requirements.

• list_active_crawls

  Retrieve all currently running web crawls for the authenticated team. Returns a list of active crawl operations with their current status and progress.

• list_batch_scrape_errors

  Retrieve all errors that occurred during a batch scraping job. Use this to diagnose failures and understand which URLs or data extraction steps encountered issues.

• list_crawl_errors

  Retrieve all errors encountered during a specific crawl job. Returns detailed error information to help diagnose and troubleshoot crawling issues.

• list_credit_usage_history

  Retrieve the credit usage history for the authenticated team. Optionally filter results to show credit consumption broken down by individual API keys.

• list_token_usage_history

  Retrieve historical token usage data for the authenticated team. Optionally break down usage by individual API keys.

• scrape_and_extract_urls

  Scrape content from multiple URLs and extract structured information using LLM-powered analysis. Supports batch processing with optional intelligent data extraction.

• scrape_and_extract_webpage

  Scrapes content from a specified URL and uses LLM-powered extraction to identify and structure relevant information from the page.

• search_and_scrape_resultswrite action

  Execute a web search and optionally scrape detailed content from the results. Supports time-based filtering, location-specific searches, and customizable scraping behavior.

• Code scan5 source files scanned25/25
• –Live reliabilityno gateway calls yet and no remote to proben/a
• –Tool poisoningtools not inspected (local package is not executed); not countedn/a
• Auth qualitylocal package, no credentials required12/15
• Maintenancelast push 138 days ago8/15
• Maintainer identityregistry namespace matches repository owner7/10

Safety score

80/100

higher than 55% of 866 Scraping and browsing servers

Tools

22

the typical Scraping and browsing server has 6

Tools that change things

14%

typical: 0%. Fewer write tools means less an agent can break

GitHub stars

31

more than 87% of 583 Scraping and browsing servers

Downloads a week

159

more than 66% of 309 Scraping and browsing servers with a package

Firecrawl: common questions

Is Firecrawl MCP server safe?

Mostly: it is graded B (80/100). Read the Firecrawl safety report

How do I install Firecrawl?

It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.

Does Firecrawl need an API key?

Not as far as the registry entry and our scan can tell: no credentials are declared or required.

Is Firecrawl maintained?

The last commit was 176 days ago (2026-05-12). The latest release is v1.0.3.

What can I use instead of Firecrawl?

Servers from other publishers that do the same job: Crawlberg MCP server, Kreuzcrawl MCP server and MCP server. Compare all Firecrawl alternatives.

How does Firecrawl compare with other Scraping and browsing MCP servers?

safety score 80/100 (higher than 55% of 866 Scraping and browsing servers); tools 22 (the typical Scraping and browsing server has 6); tools that change things 14% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.