← Catalogue
appseed

Firecrawl

Crawl and extract clean page content for LLM pipelines. A common agent research tool and a Leyline evidence source class.

MCP declaredAPI declaredCost usageLicence AGPL-3.0

Interface

mcp

Model Context Protocol server

Interface

http

HTTP API

[ Observed sample ]

Frequency in Leyline's observed sample

The count is distinct observed stacks. It is not a Score input.

Appears in 1 distinct stacks in Leyline's observed sample.

Source: action-catalog. Method distinct-stacks. Observed 2026-10-11.

Record cmp_firecrawl

Open ranks

[ Score explain ]

Why the Score is 23

How Score works

Score v2 uses only observed signals. The displayed contribution is weight × value × 100. Missing factors are insufficient evidence.

Score factor

GitHub health

18% weight. A licence is declared. Documentation is available.

Value 0.30 · 5.4 points

18% weight × 0.30 value

5.4 points

A licence is declared. Documentation is available.

Score factor

Agent use

16% weight. insufficient evidence

insufficient evidence

insufficient evidence

insufficient evidence

insufficient evidence

Score factor

Human notes

14% weight. 1 stored human notes (component-record).

Value 0.09 · 1.2 points

14% weight × 0.09 value

1.2 points

1 stored human notes (component-record).

Score factor

Composability

16% weight. insufficient evidence

insufficient evidence

insufficient evidence

insufficient evidence

insufficient evidence

Score factor

Checklist

10% weight. An MCP surface is declared. An API is declared. Cost is usage. 3 of 3 checklist fields are complete.

Value 1.00 · 10.0 points

10% weight × 1.00 value

10.0 points

An MCP surface is declared. An API is declared. Cost is usage. 3 of 3 checklist fields are complete.

Score factor

Evidence quality

14% weight. 3 sources cover 3 evidence types. The latest dated evidence is 2026-09-12. Freshness is omitted unless observed as a signal.

Value 0.46 · 6.5 points

14% weight × 0.46 value

6.5 points

3 sources cover 3 evidence types. The latest dated evidence is 2026-09-12. Freshness is omitted unless observed as a signal.

Score factor

Benchmarks

12% weight. insufficient evidence

insufficient evidence

insufficient evidence

insufficient evidence

insufficient evidence

Total23.08 → 23 after rounding

Agent use: insufficient evidence

Composability: insufficient evidence

Benchmarks: insufficient evidence

[ Claims ]

Publisher-asserted record

Claims are what the publisher declares. Score uses observed signals, not these assertions, except for checklist fields derived from interfaces. MCP, API, cost, and license claims are marked verified, unverified, or contradicted from intake evidence.

Kind
app
Interfaces

Interface

mcp

Model Context Protocol server

Interface

http

HTTP API

Functions

Function

Crawl

walk the public web

Crawl Browse Crawl

Function

Extract

pull a fact or field out

Extract Browse Extract

Function

Ingest

bring raw material in

Ingest Browse Ingest

Function

Connect

speak a protocol (MCP, API, CLI)

Connect Browse Connect
Tags
Subject

subject

Web content

The tool fetches or searches public web pages and returns their content.

Web content Browse Web content

[ Capability slices ]

Compose the useful parts.

ingest

Ingest

Crawl and extract clean page content for LLM pipelines. A common agent research tool and a Leyline evidence source class.

search

Search

Crawl and extract clean page content for LLM pipelines. A common agent research tool and a Leyline evidence source class.

connect

Connect

Crawl and extract clean page content for LLM pipelines. A common agent research tool and a Leyline evidence source class.

Clean scrape/crawl API and MCP. Self-host path lowers glue cost. Rate limits and JS-render variance are the main blocks.

[ Relations ]

Derived alternatives and shared slots

  • Fills the same slot as
    Context.dev Shared functions connect, crawl, extract, search. Can fill the same function slot.
  • Alternative to
    Search1API Shared functions crawl, extract, search. Same kind and overlapping capability.
  • Alternative to
    TinyFish Shared functions connect, crawl, extract, search. Same kind and overlapping capability.
  • Alternative to
    Exa Shared functions connect, crawl, extract, search. Same kind and overlapping capability.
  • Fills the same slot as
    VUDA (Visual UI Debug Agent) Shared functions connect, crawl, extract, search. Can fill the same function slot.
  • Fills the same slot as
    Soar Shared functions connect, search. Can fill the same function slot.
  • Fills the same slot as
    Local FAISS MCP Server Shared functions connect, extract, ingest, search. Can fill the same function slot.
  • Fills the same slot as
    PulseMCP Shared functions connect, ingest, search. Can fill the same function slot.

[ Signals ]

Observed evidence and source claims

Signals carry source, method, and observedAt. Source review dates and evidence basis are shown separately. Unobserved metrics stay insufficient evidence.

  • github
    firecrawl/firecrawl

    Evidence basis unknown · Check date unknown · Source date 2026-09-12

  • docs
    Firecrawl docs

    Evidence basis unknown · Check date unknown · Source date 2026-09-12

  • tweet
    DFIR Lab CVE note

    Evidence basis unknown · Check date unknown · Source date 2026-09-12

Introducing the new Firecrawl. Plus, instant onboarding with OAuth for humans and a keyless version for agents. Get agent-ready web context in any MCP client ...

Source: x.com

The API to search, scrape, and interact with the web at scale. powered by industry-leading search and scraping designed for agents. less now your ai agents can ...

Source: x.com

firecrawl is a top three web search api for ai agents with the best quality/price tradeoff out there and we're shipping improvements every week.

Source: x.com
Suggest a correction

Propose a change with a public source. Corrections wait for review before the card changes.

[ Notes ]

humanConcept note lists Firecrawl as a crawl-class example, not the product to clone.