ajeetraina777/sbx-kits-firecrawl:latest

schemaVersion: "2"
kind: mixin
name: firecrawl
displayName: Firecrawl (live web access)
description: 'Adds live web search/scrape/crawl to any agent via the firecrawl-py SDK, wired to Firecrawl''s cloud API. Needs a key: sbx secret set -g firecrawl (the kit holds no key).'
agentInstructions:
    content: |
        Firecrawl live web access: the firecrawl-py SDK is installed and the
        FIRECRAWL_API_KEY credential is injected by the sbx proxy on requests to
        api.firecrawl.dev. Use it for current, LLM-ready web data:

            from firecrawl import Firecrawl
            fc = Firecrawl()                                 # key handled by the sbx proxy

            fc.scrape("https://example.com", formats=["markdown"])   # one page -> clean markdown
            fc.search("docker sandboxes mixin kit", limit=5)         # search the web, get page content
            fc.crawl("https://docs.example.com", limit=20)           # crawl a whole site/section

        Reach for this whenever a task needs facts beyond your knowledge cutoff, the
        contents of a specific URL, or a sweep across a documentation site.
permissions:
    network:
        allow:
            - pypi.org
            - files.pythonhosted.org
            - api.firecrawl.dev
credentials:
    - service: firecrawl
      apiKey:
        name: FIRECRAWL_API_KEY
        inject:
            - domain: api.firecrawl.dev
              header: Authorization
              format: Bearer %s
environment:
    variables:
        FIRECRAWL_API_KEY: proxy-managed
setup:
    install:
        - command: pip install --break-system-packages 'firecrawl-py==4.30.1'
          user: "1000"
          description: Install the Firecrawl Python SDK