Skip to main content
Firecrawl Local is one binary that scrapes, crawls and maps websites from your own machine. It turns pages into clean markdown, plugs into AI agents as an MCP server, and serves the Firecrawl v2 API on localhost, so code written for Firecrawl runs against it unchanged. There is no database, queue or container to run. Pages are fetched and cleaned on your machine with the same cleaning code the Firecrawl API uses. Search, pages that refuse your machine, and Alexandria data providers go to Firecrawl Cloud, which you can turn off. The source is in apps/local of the Firecrawl repository.

Choose Firecrawl Local, self-hosting or Firecrawl Cloud

Install

You need Rust and a C compiler. On macOS, install the Xcode command line tools with xcode-select --install. On Debian and Ubuntu, install build-essential. Then install Firecrawl Local from crates.io.
To build the latest code instead, clone the repository and build apps/local. The binary lands in target/release/firecrawl-local.
Two optional extras unlock more of it.
  • Chrome or Chromium. Firecrawl Local renders pages that need JavaScript in the browser already installed on your machine. Without one, static pages still work and a page that needed a browser comes back with a warning saying so.
  • Node.js 22 or newer. The MCP server is the firecrawl-mcp npm package, which Firecrawl Local runs through npx.

Quick start

Scrape a page and print its markdown.
Crawl a site and save one markdown file per page.
List every URL on a site.
Without --markdown, scrape prints the same JSON the Firecrawl API returns. Ask for more formats with --format markdown,links. The choices are markdown, html, rawHtml and links. PDFs and Office documents are parsed on your machine too.

Add it to your AI agent

init adds Firecrawl Local as an MCP server to every AI tool it finds on your machine.
It knows Claude Code, Claude Desktop, Cursor, Windsurf, Gemini CLI and Codex. It backs up each config file before changing it. Add --dry-run to see the changes without writing them, or --agent cursor to set up one tool. Restart the tool afterwards so it loads the new server. To add it by hand, register firecrawl-local mcp as a stdio MCP server. In a JSON config that looks like this, with the full path to the binary.
Your agent gets the standard Firecrawl MCP tools. Scrape, crawl, map and batch scrape run on your machine, and the other tools go to Firecrawl Cloud.

Run the Firecrawl API locally

serve answers the Firecrawl v2 API on port 3002.
From another terminal, scrape a page through it.
Point any Firecrawl SDK at it by setting its API URL to http://localhost:3002. No API key is needed for local routes.
These routes run on your machine. Every other /v2 route, such as /v2/search, is passed on to Firecrawl Cloud unless FIRECRAWL_CLOUD says otherwise. The v0 and v1 routes are not served. Crawl and batch jobs live in memory and expire an hour after they start.

Commands

Run firecrawl-local <command> --help for every option.

What runs where

Scraping, crawling, mapping and document parsing run on your machine and send nothing to Firecrawl. Three things need Firecrawl Cloud because a laptop does not have the index, the network or the data. A page Firecrawl Cloud fetched for you carries "source": "firecrawl-cloud". If the cloud cannot get it either, the result has "blocked": true and a warning that says why. Cloud calls carry a random install ID and the name of the tool that made them, which is how Firecrawl counts installs. To sign in, run login. It opens the browser and saves your API key in the same place the Firecrawl CLI keeps it, so either tool’s login works for both.
A running serve picks up the login straight away, and so do the MCP server’s search and scrape tools. The MCP server’s Alexandria tools check for a key when they start, so restart your AI tool after signing in to use them. FIRECRAWL_CLOUD controls the hand-off. An unrecognised value counts as off. login always talks to Firecrawl, because signing in is its job.

Security

The defaults differ between the tools you run yourself and the API server, because the API takes requests from other programs.
  • scrape, crawl, map and mcp run for the person at the keyboard, so they can reach localhost and your private network. scrape, crawl and mcp take --public-only to refuse those addresses.
  • serve listens on 127.0.0.1 and refuses localhost and private addresses unless you pass --allow-private. Binding another address with --host requires --token, and requests are checked against an allowed Host list that --allowed-host adds to.
  • Always refused. Link-local and cloud metadata addresses are blocked in every mode, including after redirects and DNS resolution.
An AI agent that reads a page with hidden instructions could be steered into opening an internal URL. If your agent browses sites you do not trust, register the MCP server as firecrawl-local mcp --public-only.
The same rules cover the browser. Chrome runs headless and sandboxed with a throwaway profile, behind a loopback proxy inside Firecrawl Local that checks every connection it opens, including redirects, subresources, script requests and WebSockets. Firecrawl Local identifies itself in its User-Agent and reads robots.txt when crawling, where site owners can address it as FirecrawlLocal.

Running in Docker

Chrome keeps its sandbox on, which needs user namespaces, and Docker’s default seccomp profile blocks them. To render JavaScript pages in a container, use a profile that keeps Docker’s defaults and also allows clone, setns and unshare. Playwright publishes one.
Do not use seccomp=unconfined for this. It removes the whole filter from a container that loads pages you do not control.

Configuration

Limits

  • Local scrapes skip the json and summary formats with a warning, and ignore browser actions. Screenshots need Chrome.
  • Crawl and batch jobs are kept in memory, so they end when serve stops.
  • The v0 and v1 API routes are not served.
For a full Firecrawl server with queues, workers and every format, see Self-hosting.