# Firecrawl launches Alexandria, one-connection data access for LLM agents

> Updated 2026-09-23 · type: news · category: data-scraping · status: active · rev 1

Firecrawl's Alexandria gives LLM agents one-connection access to data providers, indexes and datasets for extraction via MCP, CLI or API.

- Open source: no
- Last verified: 2026-09-23

- **Canonical:** https://gtmstacker.com/registry/news/firecrawl-alexandria/
- **Source:** [Product Hunt · Firecrawl](https://www.producthunt.com/products/extract-by-firecrawl)
- **Tags:** data-scraping, prospecting-enrichment, news, extraction, llm-agents, hosted

## Is Firecrawl launches Alexandria, one-connection data access for LLM agents open source?

No, Firecrawl launches Alexandria, one-connection data access for LLM agents is not open source.


---

Alexandria is a hosted Firecrawl offering that gives LLM agents single-connection access to data providers, specialized indexes and datasets for extraction, reachable via MCP, CLI or API. It is built on top of Firecrawl — whose core engine is open source at github.com/mendableai/firecrawl — but Alexandria itself is a hosted data-access product, not open source, and carries no SPDX license. It offers free options plus provider-specific pricing.

## Notes

- What is confirmed: Alexandria is a Firecrawl offering that gives LLM agents one-connection access to data providers, specialized indexes and datasets for extraction, available via MCP, CLI and API, with free options plus provider-specific pricing (WebFetch 2026-09-23).
- Licensing precision: Firecrawl's core engine is OSS at github.com/mendableai/firecrawl, but Alexandria is a hosted product on top of it — it is not open source and no SPDX license attaches to it. Do not treat Alexandria as OSS.
- What is vendor-claimed (tagged, not treated as fact): "+21% answer quality vs built-in web tools."
- The GTM-stack read: prospecting and enrichment increasingly means getting agents clean access to many data sources, and the friction is per-provider plumbing. Alexandria's pitch is to collapse that into one connection spanning providers, indexes and datasets — the scrape-to-enrich data layer for AI-native extraction. Evaluate it as hosted infrastructure (billed by provider) rather than a self-hostable open component, and price the vendor's quality-lift claim as unverified.
- Curated from the GTM Stacker signal registry (2026-09-23 pass: studio discovery lane).