Firecrawl

Web data and browser automation

Independent review. IonBin has no partnership with Firecrawl and was not paid for this page. Our evaluation is our own, based on public documentation and our research. Product names are trademarks of their owners and are used for identification only. How disclosure works.

An API that turns web pages into clean markdown or structured data for AI use. Its MCP server can be used without a key to start, or with OAuth or an API key, and it has native connectors for ChatGPT and Claude.

Best for
  • Pulling public page content into an AI workflow
  • Monitoring competitor or docs pages for changes
Not for
  • Pages behind logins you aren't allowed to automate
  • Scraping against a site's terms

Top use cases

  • Scrape a page to markdown for a summary source ↗
  • Parse a document into text an AI client can use source ↗
  • Search the web and return page content in one step source ↗

In depth

MCP server

Firecrawl's docs offer three ways to connect. Keyless access, with no account, covers Search, Scrape and Parse within daily limits. Sign-in uses OAuth at https://mcp.firecrawl.dev/v2/mcp-oauth, and API-key connections use https://mcp.firecrawl.dev/v2/mcp. Native connectors are listed for ChatGPT, Codex and Claude. Checked 2026-10-18. source ↗

Plans

The free tier includes 1,000 credits. Hobby is $16 a month for 5,000 credits and Standard $83 a month for 100,000 credits, both billed yearly. Checked 2026-10-18. source ↗

How to use it with AI

How Firecrawl connects to each AI platform: native connector or MCP, API through code the agent writes, browser control, or file upload.

PlatformMCP / connectorAPI (agent-written code)BrowserUpload / export
Claude (incl. Claude Code) Not documented Native connector listed in Firecrawl's docs. A named plugin, skill or CLI does not by itself establish an MCP/native connector pairing. Verify the route and client setup. Firecrawl named integration docs ↗Claude (incl. Claude Code) MCP docs ↗ Not documented Claude (incl. Claude Code): Claude Code edits files and runs commands Firecrawl publishes an API, but this pairing still needs network, authentication and execution-scope checks. Firecrawl API ↗Claude (incl. Claude Code) docs ↗ Inferred Claude Code with the Claude in Chrome extension (Chrome, Edge and other Chromium browsers). Firecrawl is a web app; the pairing itself is not documented. Claude (incl. Claude Code) browser docs ↗ Not documented Verify which side exports and which imports, supported formats and permissions. Firecrawl's recorded upload/import status is to-verify; Claude (incl. Claude Code)'s file status is yes. These flags do not establish a file-transfer route. Claude (incl. Claude Code) file docs ↗
OpenAI Codex Not documented Firecrawl has an official MCP server and OpenAI Codex supports MCP, but Firecrawl's docs don't name this pairing. Auth setup may differ. Firecrawl MCP docs ↗OpenAI Codex MCP docs ↗ Not documented OpenAI Codex: Edits files and runs commands locally; cloud tasks run in isolated workspaces Firecrawl publishes an API, but this pairing still needs network, authentication and execution-scope checks. Firecrawl API ↗OpenAI Codex docs ↗ Inferred Only in the ChatGPT desktop app; not in the Codex CLI or IDE extension. Firecrawl is a web app; the pairing itself is not documented. OpenAI Codex browser docs ↗ Not documented Verify which side exports and which imports, supported formats and permissions. Firecrawl's recorded upload/import status is to-verify; OpenAI Codex's file status is yes. These flags do not establish a file-transfer route. OpenAI Codex file docs ↗
Google Antigravity Not documented Firecrawl has an official MCP server and Google Antigravity supports MCP, but Firecrawl's docs don't name this pairing. Auth setup may differ. Firecrawl MCP docs ↗Google Antigravity MCP docs ↗ Not documented Google Antigravity: Agents edit code and run tasks Firecrawl publishes an API, but this pairing still needs network, authentication and execution-scope checks. Firecrawl API ↗Google Antigravity docs ↗ Inferred The /browser guide documents App and CLI support through Chrome DevTools MCP; the overview comparison conflicts on CLI availability. IDE browser features are separate. Firecrawl is a web app; the pairing itself is not documented. Google Antigravity browser docs ↗ Not documented Verify which side exports and which imports, supported formats and permissions. Firecrawl's recorded upload/import status is to-verify; Google Antigravity's file status is yes. These flags do not establish a file-transfer route. Google Antigravity file docs ↗

Firecrawl's docs also name: ChatGPT.

Confirmed is reserved for evidence of the specific connection route. The current named integrations include plugins, skills and CLIs, so a named platform alone does not confirm MCP or a native connector. Inferred means each side documents a relevant capability, but no document describes the pairing. Code execution still needs network and credential access; file handling still needs a compatible format and transfer direction. Not documented means the records do not establish the route. IonBin has not tested these pairings. Recorded Oct 18, 2026.

Agent compatibility

MCPAPI/CLI File import?
LevelStatusDetail / source
Native connector / MCPYes Official docs ↗
API / CLIYes Official docs ↗ — REST API and SDKs
Browser / manualNo Browser access is recorded alongside a documented programmatic route.
File upload / importTo verify Batch and crawl tools not reviewed for this page

Recorded Oct 18, 2026. Setup and plan limits vary; check the vendor's docs. How levels are assigned.

Appears in these proposed stacks

Connection capabilities to compare

An official MCP server is documented for this tool. These platforms separately document MCP client support: ChatGPT, Claude, Cursor, Gemini (Google), Google Antigravity, Grok, Grok Bot, Lindy, LM Studio, Mistral Vibe, OpenAI Codex. This inventory does not establish compatible transport, authentication or actions for a pairing. Check the connection matrix and linked sources.

Automation hubs to assess for a custom API connection: Gumloop, Make, n8n, Zapier. Verify credentials, supported requests, limits and error handling; no configured integration is implied.

Review

No long-form review yet. Verdict is based on research, not hands-on testing.

Alternatives

Apify

Web data and browser automation

Cloud platform of ready-made scrapers ("Actors") and automation. Its hosted MCP server at mcp.apify.com lets AI assistants run Actors and get structured web data back.

MCPAPI/CLI
Research

Exa

Web data and browser automation

A web search API built for AI applications, returning results and page contents. Exa hosts an MCP server you can try without an API key, and the API is priced per thousand requests.

MCPAPI/CLI
Research

Tavily

Web data and browser automation

A search and extraction API for AI agents, with a free monthly credit allowance. Tavily runs a remote MCP server that connects with an API key or OAuth.

MCPAPI/CLI
Research