Firecrawl's Universal Scrape adds provider data to its /scrape endpoint

October 8, 2026Source: Firecrawl

Firecrawl has introduced Universal Scrape, an extension of its /scrape endpoint that lets developers pull web pages, files and third-party provider data through a single API. According to the company, the goal is to give AI agents more context without requiring separate scrapers, file parsers or API integrations.

Key points

Firecrawl introduced Universal Scrape, extending its /scrape endpoint beyond web pages and files.
Through Alexandria, it reaches provider data including people profiles, financial data and podcasts.
Firecrawl says Alexandria has more than 200 providers, with more being added every day.
Provider calls use the Firecrawl API key and are billed in Firecrawl credits at each tool's listed price.
Some providers, such as Particle, require an org admin to accept provider terms first.

What Universal Scrape covers

Firecrawl says its service already handles rendering, retries and parsing for web pages and files. Universal Scrape builds on that by adding access to provider data through Alexandria, Firecrawl's library of providers, all via the same endpoint.

The company lists several categories of data:

Web pages and files: dynamic websites, PDFs and images, along with Word documents, spreadsheets and presentations available by URL.
People and company profiles: professional and company data through providers including Apollo, FullEnrich and Data Legion.
Financial data: company financials and market information through providers such as Fiscal.ai and Benzinga.
Podcasts: relevant episodes and conversations through Particle, with tools for podcast search, lookup and transcripts.

Firecrawl says Alexandria has more than 200 providers and that Universal Scrape already works with a growing selection of them. The company adds that it is adding providers to Alexandria every day and bringing more of that library into /scrape.

How it works for developers

Existing Firecrawl users can keep scraping pages and documents as before and add provider data when needed. Both use the same Firecrawl API key. According to Firecrawl, provider calls are billed in Firecrawl credits at each tool's listed price.

For a web page or supported document, developers send its URL. For provider data, they call a supported Alexandria capability through the same endpoint. Firecrawl also says some supported profile URLs route directly to a user's configured enrichment providers.

The company's example uses the latest firecrawl SDK with the FIRECRAWL_API_KEY environment variable set. One call scrapes https://www.firecrawl.dev and requests markdown. A second call runs Particle's podcast search through /scrape, using the capability podcasts/episodes/search with the semantic search term "AI agents" and a limit of 2. According to Firecrawl, this returns matching transcript segments.

Before running the podcast call, an org admin must accept Particle's provider terms. Firecrawl points to its Scrape docs for URL routing and its Alexandria docs for finding and calling provider tools.

What it means for users

For teams building agents, the change is aimed at reducing integration work. Instead of wiring up a separate scraper, a file parser and several data APIs, developers can reach those sources through one endpoint and one API key, with provider usage billed in Firecrawl credits.

Firecrawl says Universal Scrape can be used in applications developers build, or connected to an agent through MCP or the CLI. The company says it will keep expanding what is reachable through /scrape, with the aim that a new source gives an agent more to work with "without giving you another integration to maintain," in the words of the Firecrawl announcement.