firecrawl/sbx-kit-firecrawl:latest

schemaVersion: "3"
displayName: Firecrawl (live web access)
author: Firecrawl <[email protected]>
description: 'Adds live web search, scrape and crawl to any sandboxed agent via the firecrawl-py SDK, wired to Firecrawl''s cloud API through the sandbox proxy. Needs a key: sbx secret set firecrawl (the kit holds no key). Layer it onto a shell or agent workload; the SDK is then importable from python3.'
sourceUrl: https://github.com/firecrawl/firecrawl-docker-sandbox
iconUrl: https://raw.githubusercontent.com/firecrawl/firecrawl-docker-sandbox/main/docs/firecrawl-sbx-kit.png
version: 1.0.0
licenses:
    - Apache-2.0
kind: mixin
provides:
    - [email protected]
capabilities:
    - type: com.docker.sandbox/network-policy@1
      config:
        install:
            allow:
                - pypi.org
                - files.pythonhosted.org
        runtime:
            allow:
                - api.firecrawl.dev
    - type: com.docker.sandbox/credential@1
      config:
        apiKey:
            inject:
                - domain: api.firecrawl.dev
                  format: Bearer %s
                  header: Authorization
            name: FIRECRAWL_API_KEY
            proxyManaged: true
        phase: runtime
        service: firecrawl
      description: Firecrawl API key (fc-...) from https://www.firecrawl.dev/app/api-keys
    - type: com.docker.sandbox/lifecycle@1
      config:
        install:
            - command: |
                set -eu
                SDK_VERSION="4.44.0"

                command -v python3 >/dev/null 2>&1 || {
                  echo "firecrawl kit: python3 not found. Every Docker sandbox template ships python3 and python3-pip; on a custom base image, install them before layering this kit." >&2
                  exit 1
                }
                python3 -m pip --version >/dev/null 2>&1 || {
                  echo "firecrawl kit: python3 is present but has no pip module. Install python3-pip on the base image." >&2
                  exit 1
                }

                # Debian and Ubuntu mark the system Python externally managed
                # (PEP 668), so a --user install needs --break-system-packages
                # there. Retry without it for images whose pip predates 23.0 and
                # rejects the flag. pip verifies the wheel against PyPI's hashes,
                # so pinning the version pins the content.
                install_sdk() {
                  python3 -m pip install --user --no-cache-dir --disable-pip-version-check "$@" "firecrawl-py==${SDK_VERSION}"
                }
                install_sdk --break-system-packages || install_sdk

                python3 -c "
                import firecrawl, importlib.metadata as m
                got = m.version('firecrawl-py')
                assert got == '${SDK_VERSION}', 'expected ${SDK_VERSION}, got ' + got
                print('firecrawl-py', got, 'installed at', firecrawl.__file__)
                "
              description: Install the Firecrawl Python SDK (firecrawl-py) as the agent user
              env:
                - HTTP_PROXY
                - HTTPS_PROXY
                - NO_PROXY
                - http_proxy
                - https_proxy
                - no_proxy
              user: "1000"
    - type: com.docker.sandbox/agent-context@1
      config:
        contentFile: /usr/share/sandbox/kit/firecrawl/firecrawl-context.md
args:
    sdkVersion:
        default: 4.44.0
        description: firecrawl-py release to install. Bump the default together with the pin in ../spec.yaml and README.md (kitcheck asserts they agree).
        pattern: ^[0-9]+\.[0-9]+\.[0-9]+$
        buildArg: SDK_VERSION