Skip to content

Browser Automation MCP Server

Firecrawl MCP Server

MCP server for Firecrawl web scraping, structured data extraction and web search integration.

Scan found nothing by firecrawl5,780MITJavaScriptBeginnerstdio
View on GitHub Install Guide

Install

Claude Code

claude mcp add firecrawl-mcp-server -- npx -y firecrawl-mcp-server

Safety Report

100% Scan found nothing
Scanned 5 months ago
7 passed
Security
Authentication
details

API key authentication via FIRECRAWL_API_KEY environment variable; supports both cloud and self-hosted deployments

Pass
CORS Policy
details

stdio MCP transport; no CORS surface on the MCP layer

N/A
Rate Limiting
details

Automatic rate limit handling with exponential backoff and configurable retry mechanisms

Pass
Known CVEs
details

No known CVEs; well-maintained by the Firecrawl/Mendable team

Pass
Code Quality
Dependency Audit
details

Node.js project; no published dependency audit but maintained by Firecrawl/Mendable team

Info
Dangerous Patterns
details

No dangerous code patterns detected

Pass
License
details

MIT License

Pass
Code Source
details

Open source under MIT License at github.com/mendableai/firecrawl-mcp-server

Pass
Community
Maintenance Status
details

Actively maintained by the Firecrawl team with community contributions

Pass

Learn about our security methodology →

Compatibility

Claude Codestdio MCP; install via npx and set FIRECRAWL_API_KEY
Not Tested
CursorListed in official MCP integrations; configure via mcp.json
Not Tested
VS CodeWorks with VS Code MCP extensions
Not Tested
WindsurfStandard stdio MCP; compatible
Not Tested
Claude DesktopFully supported; configure in claude_desktop_config.json with API key
Not Tested

Tools Provided (14)

firecrawl_scrape

Extract content from a single URL with output in JSON, markdown, or other formats

firecrawl_batch_scrape

Retrieve content from multiple known URLs with parallel processing

firecrawl_check_batch_status

Monitor the progress of a batch scraping operation

firecrawl_map

Discover and list all indexed URLs on a website

firecrawl_search

Search the web and optionally extract content from search results

firecrawl_crawl

Asynchronously crawl multiple related pages on a website

firecrawl_check_crawl_status

Monitor the progress of an ongoing crawl job

firecrawl_extract

Extract structured information from web pages using LLM capabilities with a defined schema

firecrawl_agent

Run an autonomous research agent for complex multi-source data gathering tasks

firecrawl_agent_status

Check research agent progress and retrieve accumulated results

firecrawl_browser_create

Establish a cloud browser session for interactive web automation

firecrawl_browser_execute

Run code (bash, Python, JavaScript) within an active browser session

firecrawl_browser_list

List all currently active cloud browser sessions

firecrawl_browser_delete

Terminate and clean up a cloud browser session

Frequently Asked Questions

What is Firecrawl MCP Server?

MCP server for Firecrawl web scraping, structured data extraction and web search integration.

What tools does Firecrawl MCP Server provide?

Firecrawl MCP Server provides 14 tools including firecrawl_scrape, firecrawl_batch_scrape, firecrawl_check_batch_status, firecrawl_map. Each tool can be called by AI agents to perform specific operations.

Is Firecrawl MCP Server safe to use?

We cannot tell you that, and nobody scanning at this scale can. What we did in March 2026 was shallow-clone Firecrawl MCP Server and run five keyword searches over its source: auth identifiers, CORS configuration, rate-limit identifiers, the dependency manifest against a hardcoded list of 18 known-vulnerable packages, and unguarded eval/exec calls. None of them matched. A text search cannot follow a variable, judge intent, or tell you what a server does once it is running, so "nothing matched" is not "safe". What the scan does and does not cover is written out at /mcp/security.

What are alternatives to Firecrawl MCP Server?

Similar MCP servers include Scrapling MCP Server, Chrome DevTools MCP, Playwright MCP. Each serves a similar purpose but may differ in features, language, and compatibility.

Similar MCP Servers

Scrapling MCP Server

Scan flagged something
by D4Vinci

Web scraping with stealth HTTP, real browsers, and Cloudflare bypass. CSS selectors supported.

browser automation Python stdio
claude mcp add scrapling -- uvx scrapling
30.2k 6 tools
View

Chrome DevTools MCP

Scan flagged something
by ChromeDevTools

MCP server for Chrome DevTools

browser automation TypeScript stdio
claude mcp add chromedevtools-chrome-devtools-mcp -- npx -y chrome-devtools-mcp
29.4k 29 tools
View

Playwright MCP

Scan found nothing
by microsoft

Official Microsoft Playwright MCP server, enabling LLMs to interact with web pages through structured accessibility snapshots

browser automation TypeScript stdio
claude mcp add microsoft-playwright-mcp -- npx -y @playwright/mcp@latest
29k 5 tools
View
Was this helpful?

Free AI writing tools

Check a draft for AI tells, then fix what the check finds.

Stay Updated on MCP Servers

New servers, safety alerts, and install guides — weekly.