{
  "manifest_version": "1",
  "slug": "firecrawl",
  "title": "Firecrawl",
  "headline": "Self-host Firecrawl for your agents",
  "description": "Run self-hosted Firecrawl on an exe.dev VM: a private scrape and crawl API, JSON extraction with no OpenAI key, and the Firecrawl MCP server for agents.",
  "category": "ai-agents",
  "tags": [
    "firecrawl",
    "firecrawl self-host",
    "firecrawl docker",
    "firecrawl mcp",
    "web scraping api",
    "web crawler",
    "llm extraction",
    "markdown for llms",
    "claude code",
    "codex"
  ],
  "url": "https://exe.dev/deploy/firecrawl",
  "markdown_url": "https://exe-staging.dev/deploy/firecrawl.md",
  "upstream": {
    "website": "https://www.firecrawl.dev",
    "source": "https://github.com/firecrawl/firecrawl",
    "docs": "https://docs.firecrawl.dev/contributing/self-host",
    "license": "AGPL-3.0 (SDKs MIT)"
  },
  "example_vm_name": "my-firecrawl",
  "time": "15 minutes",
  "stack": [
    {
      "name": "Firecrawl API and workers 2.11.809",
      "detail": "ghcr.io/firecrawl/firecrawl in Docker Compose, from the release's own compose file",
      "port": 3002,
      "data": "~/firecrawl/.env"
    },
    {
      "name": "Playwright service",
      "detail": "Firecrawl's headless Chromium for pages that need JavaScript, built from the same release"
    },
    {
      "name": "Queue",
      "detail": "NuQ PostgreSQL, Redis and RabbitMQ in Docker; jobs and recent results, nothing to back up"
    },
    {
      "name": "Firecrawl MCP server 3.41.0",
      "detail": "firecrawl-mcp from npm, started by Claude Code and Codex over stdio"
    },
    {
      "name": "exe.dev LLM integration",
      "detail": "the model behind JSON extraction and summaries, with no API key on the VM"
    }
  ],
  "access": [
    {
      "url": "http://localhost:3002",
      "who": "private",
      "what": "the API, for agents and scripts on the VM"
    },
    {
      "url": "https://my-firecrawl.exe.xyz:3002/",
      "who": "private",
      "what": "the same API for your computer and other VMs, with a VM token"
    },
    {
      "url": "ssh my-firecrawl.exe.xyz",
      "who": "private",
      "what": "your terminal"
    }
  ],
  "delivers": [
    "Firecrawl 2.11.809 (API, workers, Playwright, PostgreSQL, Redis, RabbitMQ) in Docker Compose, restarted after a reboot",
    "A scrape that returns Markdown from a page built with JavaScript",
    "JSON extraction through exe.dev's LLM integration, with no OpenAI key on the VM",
    "The Firecrawl MCP server connected to Claude Code and Codex on the VM",
    "A Claude Code run that scrapes books.toscrape.com through Firecrawl"
  ],
  "deployable": true,
  "deploy": {
    "new_vm_url": "https://exe-staging.dev/new?prompt=Set%20up%20Firecrawl%20on%20this%20VM%20by%20following%20the%20exe.dev%20recipe%20at%20https%3A%2F%2Fexe-staging.dev%2Fdeploy%2Ffirecrawl.md%3Fvia%3Ddeploy%20from%20top%20to%20bottom.%0A%0AThe%20recipe%27s%20example%20VM%20name%20is%20my-firecrawl.%20This%20VM%27s%20name%20is%20the%20output%20of%20%60hostname%60%3A%20use%20it%20wherever%20the%20recipe%20writes%20my-firecrawl.%20Skip%20the%20step%20that%20creates%20the%20VM%3B%20you%20are%20on%20it.%0A%0AYou%20are%20done%20when%20all%20of%20these%20are%20true.%20Check%20each%20one%20yourself%3A%0A-%20Firecrawl%202.11.809%20%28API%2C%20workers%2C%20Playwright%2C%20PostgreSQL%2C%20Redis%2C%20RabbitMQ%29%20in%20Docker%20Compose%2C%20restarted%20after%20a%20reboot%0A-%20A%20scrape%20that%20returns%20Markdown%20from%20a%20page%20built%20with%20JavaScript%0A-%20JSON%20extraction%20through%20exe.dev%27s%20LLM%20integration%2C%20with%20no%20OpenAI%20key%20on%20the%20VM%0A-%20The%20Firecrawl%20MCP%20server%20connected%20to%20Claude%20Code%20and%20Codex%20on%20the%20VM%0A-%20A%20Claude%20Code%20run%20that%20scrapes%20books.toscrape.com%20through%20Firecrawl%0A%0ARun%20the%20VM-side%20commands%20in%20%22Set%20up%20by%20hand%22%20only%3B%20skip%20creating%20the%20VM.%0AIf%20%60exeuntu%20configure%60%20reports%20an%20existing%20user%20config%2C%20leave%20it%20alone%2C%0Aand%20if%20%60~%2F.codex%2Fconfig.toml%60%20already%20has%20%60%5Bmcp_servers.firecrawl%5D%60%2C%0Adon%27t%20add%20it%20twice.%20Verify%20with%20the%20checks%20in%20that%20section.%20Don%27t%20create%0AVM%20tokens%20unless%20the%20person%20asks.%20Finish%20by%20showing%20the%20Claude%20Code%0Aanswer%2C%20and%20tell%20the%20owner%20how%20to%20reach%20the%20API%20from%20their%20computer%0A%28%22Use%20it%20from%20your%20computer%20or%20another%20VM%22%29.%0A%0AFinish%20with%20the%20URLs%20I%20should%20open.%0A",
    "terminal": "curl -fsSL https://exe-staging.dev/deploy/firecrawl/prompt.txt | ssh exe.dev new --prompt=/dev/stdin",
    "prompt": "Set up Firecrawl on this VM by following the exe.dev recipe at https://exe-staging.dev/deploy/firecrawl.md?via=deploy from top to bottom.\n\nThe recipe's example VM name is my-firecrawl. This VM's name is the output of `hostname`: use it wherever the recipe writes my-firecrawl. Skip the step that creates the VM; you are on it.\n\nYou are done when all of these are true. Check each one yourself:\n- Firecrawl 2.11.809 (API, workers, Playwright, PostgreSQL, Redis, RabbitMQ) in Docker Compose, restarted after a reboot\n- A scrape that returns Markdown from a page built with JavaScript\n- JSON extraction through exe.dev's LLM integration, with no OpenAI key on the VM\n- The Firecrawl MCP server connected to Claude Code and Codex on the VM\n- A Claude Code run that scrapes books.toscrape.com through Firecrawl\n\nRun the VM-side commands in \"Set up by hand\" only; skip creating the VM.\nIf `exeuntu configure` reports an existing user config, leave it alone,\nand if `~/.codex/config.toml` already has `[mcp_servers.firecrawl]`,\ndon't add it twice. Verify with the checks in that section. Don't create\nVM tokens unless the person asks. Finish by showing the Claude Code\nanswer, and tell the owner how to reach the API from their computer\n(\"Use it from your computer or another VM\").\n\nFinish with the URLs I should open.\n",
    "prompt_url": "https://exe-staging.dev/deploy/firecrawl/prompt.txt"
  },
  "published": "2026-11-21",
  "updated": "2026-11-21",
  "verified": "2026-11-21",
  "related": [
    "scrapling",
    "browser-use",
    "claude-code",
    "codex",
    "cloud-browser",
    "docker-compose"
  ],
  "alternatives": [
    "Firecrawl Cloud",
    "Apify"
  ],
  "files": [
    "https://exe-staging.dev/deploy/firecrawl/crawl.py"
  ]
}
