Firecrawl

OpenClaw can use Firecrawl in three ways:

• as the
  text

  Copy

  web_search
  provider
• as explicit plugin tools:
  text

  Copy

  firecrawl_search
  and
  text

  Copy

  firecrawl_scrape
• as a fallback extractor for
  text

  Copy

  web_fetch

It is a hosted extraction/search service that supports bot circumvention and caching, which helps with JS-heavy sites or pages that block plain HTTP fetches.

Get an API key

1. Create a Firecrawl account and generate an API key.
2. Store it in config or set
   text

   Copy

   FIRECRAWL_API_KEY
   in the gateway environment.

Configure Firecrawl search

json5
Copy
{
  tools: {
    web: {
      search: {
        provider: "firecrawl",
      },
    },
  },
  plugins: {
    entries: {
      firecrawl: {
        enabled: true,
        config: {
          webSearch: {
            apiKey: "FIRECRAWL_API_KEY_HERE",
            baseUrl: "https://api.firecrawl.dev",
          },
        },
      },
    },
  },
}

Notes:

• Choosing Firecrawl in onboarding or
  text

  Copy

  openclaw configure --section web
  enables the bundled Firecrawl plugin automatically.
• text

  Copy

  web_search
  with Firecrawl supports
  text

  Copy

  query
  and
  text

  Copy

  count
  .
• For Firecrawl-specific controls like
  text

  Copy

  sources
  ,
  text

  Copy

  categories
  , or result scraping, use
  text

  Copy

  firecrawl_search
  .
• text

  Copy

  baseUrl
  overrides must stay on
  text

  Copy

  https://api.firecrawl.dev
  .
• text

  Copy

  FIRECRAWL_BASE_URL
  is the shared env fallback for Firecrawl search and scrape base URLs.

Configure Firecrawl scrape + web_fetch fallback

json5
Copy
{
  plugins: {
    entries: {
      firecrawl: {
        enabled: true,
        config: {
          webFetch: {
            apiKey: "FIRECRAWL_API_KEY_HERE",
            baseUrl: "https://api.firecrawl.dev",
            onlyMainContent: true,
            maxAgeMs: 172800000,
            timeoutSeconds: 60,
          },
        },
      },
    },
  },
}

Notes:

• Firecrawl fallback attempts run only when an API key is available (
  text

  Copy

  plugins.entries.firecrawl.config.webFetch.apiKey
  or
  text

  Copy

  FIRECRAWL_API_KEY
  ).
• text

  Copy

  maxAgeMs
  controls how old cached results can be (ms). Default is 2 days.
• Legacy
  text

  Copy

  tools.web.fetch.firecrawl.*
  config is auto-migrated by
  text

  Copy

  openclaw doctor --fix
  .
• Firecrawl scrape/base URL overrides are restricted to
  text

  Copy

  https://api.firecrawl.dev
  .

reuses the same settings and env vars.

Firecrawl plugin tools

text

Copy

firecrawl_search

Use this when you want Firecrawl-specific search controls instead of generic

.

Core parameters:

• text

  Copy

  query
• text

  Copy

  count
• text

  Copy

  sources
• text

  Copy

  categories
• text

  Copy

  scrapeResults
• text

  Copy

  timeoutSeconds

text

Copy

firecrawl_scrape

Use this for JS-heavy or bot-protected pages where plain

is weak.

Core parameters:

• text

  Copy

  url
• text

  Copy

  extractMode
• text

  Copy

  maxChars
• text

  Copy

  onlyMainContent
• text

  Copy

  maxAgeMs
• text

  Copy

  proxy
• text

  Copy

  storeInCache
• text

  Copy

  timeoutSeconds

Stealth / bot circumvention

Firecrawl exposes a proxy mode parameter for bot circumvention (

, , or ). OpenClaw always uses plus for Firecrawl requests. If proxy is omitted, Firecrawl defaults to . retries with stealth proxies if a basic attempt fails, which may use more credits than basic-only scraping.

How

text

Copy

web_fetch

uses Firecrawl

extraction order:

1. Readability (local)
2. Firecrawl (if selected or auto-detected as the active web-fetch fallback)
3. Basic HTML cleanup (last fallback)

The selection knob is

. If you omit it, OpenClaw auto-detects the first ready web-fetch provider from available credentials. Today the bundled provider is Firecrawl.

Related

• Web Search overview -- all providers and auto-detection
• Web Fetch -- web_fetch tool with Firecrawl fallback
• Tavily -- search + extract tools