A coding agent in Docker Sandboxes runs inside an isolated VM, the sandbox controls which hosts it can reach, and credentials stay on the host behind a proxy. The same controls keep the agent from opening a docs page, reading a changelog, or looking up an API that shipped after its training cutoff, so it writes code against the version it remembers. The usual fix is to widen the allowlist until the agent can fetch anything, which hands back most of what the sandbox took away.

The Firecrawl kit gives the agent web search, page scraping, and site crawling through one added host, api.firecrawl.dev, and every page comes back as clean markdown.

Industry observers note that the Firecrawl kit is a mixin (kind: mixin): it extends whichever workload you already run rather than defining a newly introduced sandbox. Its descriptor, firecrawl/firecrawl.yaml, declares four typed capabilities:.

Industry observers note that the kit adds to the sandbox’s allowlist and does not narrow it, so everything else is set by your global sbx policy. Docker’s balanced preset allows package registries, GitHub, and a curated list of vendor domains, and returns a 403 for general websites, including most documentation sites, so Firecrawl is the agent’s route to those. Under deny-all, it is the agent’s only web host.

Recent findings suggest that kits are experimental and in Early Access, so the kit format and sbx commands may change. The steps below are current for October 2026; the repository README carries the latest.

Recent findings suggest that kit: docker.io/firecrawl/sbx-kit-firecrawl:1.0.0 on Docker Hub, for linux/amd64 and linux/arm64. Source: github.com/firecrawl/firecrawl-docker-sandbox.

1. Store the key once on the host. The command prompts for the key. Service secrets are global by default, so every sandbox that requests the firecrawl service can use it once you approve. The kit never sees the value; the proxy injects it at request time.

2. Start a sandbox with the kit. The kit is an ordinary OCI image with its descriptor in the manifest, so a version tag is all you need. Each --kit adds a mixin to the workload, and the trailing . mounts your project directory.

In a recent development, on the first run, sbx asks you to approve sending the firecrawl credential to api.firecrawl.dev. Accept the defaults. The credential is required: with no secret stored, sbx refuses to create the sandbox instead of letting the agent hit a 401 mid-task. A detached or CI run cannot answer the approval prompt, so approve interactively once or write the binding to ~/.config/sbx/credentials.yaml first.

3. Give the agent a task that needs the live web. Documentation sites are blocked under balanced, so this one has to go through Firecrawl.

The kit’s instructions tell the agent to scrape blocked hosts through Firecrawl, so it calls fc.scrape(...) unprompted. Its response, trimmed:.

Sources indicate that 4. Verify each layer. In the same session, ! runs shell commands inside the sandbox.

Industry observers note that expected: FIRECRAWL_API_KEY=proxy-managed. A real fc-... value here means the key came from somewhere other than the kit.

Expected: the page as markdown, starting with # Changelog and the latest version heading. The same URL returns a 403 to curl from inside the sandbox, so output here proves the SDK, the credential, and the network rule at once.

Recent findings suggest that the kit also describes itself inside the sandbox. This prints the published descriptor, and the agent instructions sit next to it as firecrawl-context.md:.

Running from source. To review or modify the kit before you run it, clone the repository and point --kit at the firecrawl/ directory; sbx builds source kits on demand:.

With the kit installed, the agent can look things up on the web while it works. The sandbox only needs to talk to one new address, api.firecrawl.dev, and Firecrawl fetches the pages for it. This matters because the default balanced policy blocks most documentation sites. Without the kit, you’d have to allow each site one by one, and every new site you allow makes the sandbox a little less locked down.

Industry observers note that without the kit, you had a choice to make. The default balanced policy blocks most documentation sites, so you could either leave the agent working from what it remembered, or allow sites one by one and loosen the sandbox a little each time. The kit avoids that choice. Your Firecrawl API key stays on your machine, behind the proxy, and the agent still reads the web as it is today.

The result is fewer made-up APIs, fewer failed upgrades, and less time spent correcting an agent that was confidently out of date.

It has been revealed that the kit is published under the firecrawl organization on Docker Hub as firecrawl/sbx-kit-firecrawl, with source, changelog, and CI on GitHub under Apache-2.0. The SDK pin is verified against PyPI’s package hashes at install time, and every release passes Docker’s kit-tck conformance suite in CI. Review the descriptor and allowlist before running it, as with any kit.

Sources indicate that pull the kit from Docker Hub: hub.docker.com/r/firecrawl/sbx-kit-firecrawl. Challenges and feature requests go to the GitHub repository.

Docker’s WeAreDevelopers keynote shows how Sandboxes, Kits, and Cloud Sandboxes give AI agents strong isolation and reproducible authority.

Give AI coding agents live web access with the Firecrawl kit for Docker Sandboxes. Learn to search, scrape, and crawl websites with network controls.

A container shares the host kernel. Docker Sandboxes are microVMs with their own kernel and private Docker Engine. See how they differ and when to use each.

Docker partners with ActiveState to continue to provide one standard for trusted content across everything you and your teams build on.

→ Read original article