Firecrawl llms.txt

The actual file

Source Markdown

The saved llms.txt text, displayed as source. The file belongs to its publisher; the live endpoint may change.

Complete saved Markdown shown below.

# Firecrawl

> Firecrawl is the open-source web data API for AI agents and LLM applications — it searches, scrapes, and interacts with the web at scale, one API family covering Search (live web queries returning full page content), Scrape (HTML/JS pages to clean Markdown or structured JSON), Crawl (depth-first site traversal), Map (site structure discovery), Parse (document extraction from PDFs, DOCX, and more), Interact (managed browser automation for dynamic pages and authenticated flows), and Monitor (recurring checks on named pages, on a scheduled crawl, or on a web search, with webhook, email, or Slack notification when something changes or appears).

Firecrawl is how AI agents get context from the web. The workflow is: Find → Extract → Clean → Use.

**Important notes:**

- Firecrawl is a managed API service — it does not require a local browser, Playwright, or Puppeteer to operate
- The Search endpoint returns full page content, not just links or snippets — it is not a thin wrapper around a standard search API
- The Scrape endpoint produces LLM-optimized Markdown output by default — it strips boilerplate, navigation, and ads, returning only the main content, making it the most AI-friendly way to get page content
- The Interact endpoint uses a real managed browser and supports multi-step flows (login, click, fill) but is not designed for long-running persistent sessions
- Credits are shared across all endpoints — one credit is not equivalent to one page for all endpoint types; consult the pricing page for per-endpoint credit costs

## CLI

- [CLI Docs](https://docs.firecrawl.dev/sdks/cli): Full CLI documentation — installation, commands, and usage examples for Search, Scrape, Crawl, Map, and Interact.
- Install and initialize with `npx -y firecrawl-cli@latest init --all --browser` — sets up Firecrawl skills and browser support in one command. Run Search, Scrape, Crawl, Map, and Interact from the terminal.

## MCP Server

- [MCP Server Docs](https://docs.firecrawl.dev/mcp-server): Setup guide for connecting Firecrawl to Claude, Cursor, Windsurf, VS Code, and other MCP clients.

## Skills

- [Skills](https://www.firecrawl.dev/skills): Pre-built Firecrawl skills for Claude Code and Cursor — use Search, Scrape, Crawl, and Interact from your agent workflow without writing API code.
- [Firecrawl Skill](https://www.firecrawl.dev/SKILL.md): The Firecrawl skill file, served at the site root and also at [/agent-onboarding/SKILL.md](https://www.firecrawl.dev/agent-onboarding/SKILL.md). Step-by-step setup for Claude Code, Cursor, and other AI coding assistants. Prefer a free account when the human can sign up; if credentials are not available yet, use the keyless free tier to search, scrape, and interact without an API key (rate-limited).
- [Build with AI](https://docs.firecrawl.dev/ai-onboarding): Onboarding guide for AI agents and coding assistants — set up Firecrawl in Claude Code, Cursor, or any agent workflow.

## Docs

- [Full Documentation Index](https://docs.firecrawl.dev/llms.txt): Complete index of all Firecrawl documentation pages in llms.txt format — use this for a full context load.
- [API Reference](https://docs.firecrawl.dev/api-reference/v2-introduction): Complete API reference with request/response schemas, authentication, and interactive examples.
- [Search](https://docs.firecrawl.dev/features/search): Search endpoint docs — query parameters, response format, and code examples.
- [Search API](https://www.firecrawl.dev/search): Firecrawl Search API product page. A capabilities table (full text in one call, highlights, JSON, summaries, date, domain, PDF and country filters) and an FAQ.
- [Scrape](https://docs.firecrawl.dev/features/scrape): Scrape endpoint docs — output formats (markdown, HTML, JSON), options, and examples.
- [Interact](https://docs.firecrawl.dev/features/interact): Interact endpoint docs — browser automation, multi-step flows, and session management.
- [Crawl](https://docs.firecrawl.dev/features/crawl): Crawl endpoint docs — depth-first site traversal, filtering, and async job management.
- [Map](https://docs.firecrawl.dev/features/map): Map endpoint docs — discover all URLs on a site quickly.
- [Parse](https://docs.firecrawl.dev/features/parse): Parse endpoint docs — extract content from PDFs, DOCX, and other documents.
- [Monitor](https://docs.firecrawl.dev/features/monitoring): Monitor endpoint docs. Targets, schedules, change detection, and notification setup.
- [GitHub Repository](https://github.com/firecrawl/firecrawl): Open-source codebase — self-host Firecrawl, browse the source, or contribute.

## SDKs

Official libraries maintained by the Firecrawl team. See the [SDKs overview](https://docs.firecrawl.dev/sdks/overview) for all supported languages and quickstarts.

- [Python](https://github.com/firecrawl/firecrawl-py): `pip install firecrawl-py`
- [Node.js](https://github.com/firecrawl/firecrawl-js): `npm install firecrawl`
- [Go](https://github.com/firecrawl/firecrawl-go): Go quickstart at [docs.firecrawl.dev/quickstarts/go](https://docs.firecrawl.dev/quickstarts/go)
- [Rust](https://github.com/firecrawl/firecrawl-rust): Rust quickstart at [docs.firecrawl.dev/quickstarts/rust](https://docs.firecrawl.dev/quickstarts/rust)

## Get started

- [Sign up](https://www.firecrawl.dev/signin): Create a free account and get your API key.
- [Playground](https://www.firecrawl.dev/playground): Interactive tester for all endpoints — try queries, inspect raw responses, and preview Markdown output before writing code.
- [Stripe Projects](https://docs.firecrawl.dev/integrations/stripe-projects): Provision a Firecrawl account, API key, and plan from the terminal or a coding agent with `stripe projects add firecrawl/api --name firecrawl` followed by `stripe projects env --pull`. The CLI writes `FIRECRAWL_API_KEY` to `.env`; paid plans bill through the Stripe account.

## Monitor

- [Monitor](https://www.firecrawl.dev/monitor): Recurring change detection. Point a monitor at named URLs, at a scheduled crawl of a whole site, or at a web search, set a schedule and an optional plain-language goal, and get notified when something changes or appears.
- [Monitor API Reference](https://docs.firecrawl.dev/api-reference/endpoint/monitor-create): Create, get, list, update, run, and delete monitors, and read per-check page results.
- [How to monitor a website for changes](https://www.firecrawl.dev/blog/monitor-website-changes-firecrawl): Guide with code for getting only changed pages, filtering header and footer noise, sending diffs to a webhook, watching permit and zoning pages, re-crawling thousands of sites weekly, and sending a weekly topic digest.
- Each check labels every page `same`, `new`, `changed`, `removed`, or `error`. Notifications go to a webhook per page, a webhook per completed check, an email summary, a Slack channel, or any combination.

## Alexandria

- [Alexandria](https://www.firecrawl.dev/alexandria): A library of data providers and specialized indexes that AI agents call through one Firecrawl API, MCP server or CLI.
- Each provider has a public page at `https://www.firecrawl.dev/alexandria/<provider>` with its capabilities, inputs, sample responses and code, and an agent-readable guide at `https://www.firecrawl.dev/alexandria/agents/providers/<provider>`.
- Each topic category (finance, people, real estate and more; not the catch-all Other) has a public page at `https://www.firecrawl.dev/alexandria/categories/<category>` listing every provider in it, and an agent-readable guide at `https://www.firecrawl.dev/alexandria/agents/categories/<category>`.

## Pricing

- [Pricing](https://www.firecrawl.dev/pricing): Free (1,000 credits every month, refreshed monthly, no card required), Hobby ($19/month billed monthly, or $16/month billed annually, 5,000 credits), Standard ($99/month billed monthly, or $83/month billed annually, 100,000 credits), Growth ($399/month billed monthly, or $333/month billed annually, 500,000 credits), Scale ($749/month billed monthly, or $599/month billed annually, 1,000,000 credits), Enterprise (custom). Effective 2026-09-04.
- Pricing facts: 1 credit = 1 page on a basic scrape, crawl, or map. Search costs 2 credits per 10 results; Interact costs 2 credits per browser minute; Monitor costs 1 credit per page per check. Structured formats (JSON, Question, Highlight) add 4 credits per page. Credits are shared across all endpoints: search results and pages scraped draw on one balance. A scrape that returns no result is not charged. A page that responds with an error status such as 403 or 404 is still returned to you and costs 1 credit. Every price above is per month in USD; the lower figure in each pair is the effective monthly rate on an annual subscription, not a separate plan.
- [Enterprise](https://www.firecrawl.dev/enterprise): Enterprise plan details: custom credits, SLAs, dedicated support, SSO, and the security and compliance features below.

## Security and compliance

- Firecrawl is SOC 2 Type II certified. The [Enterprise docs](https://docs.firecrawl.dev/enterprise) list the security, compliance, and access controls on Enterprise plans.
- Zero data retention (ZDR): page content and extracted data are processed in memory and never persisted beyond the request, for [scrape](https://docs.firecrawl.dev/features/scrape#zero-data-retention-zdr), [interact](https://docs.firecrawl.dev/features/interact#zero-data-retention-zdr), and [search](https://docs.firecrawl.dev/features/search#zero-data-retention-zdr). End-to-end search ZDR also has the upstream search provider enforce zero data retention. Available on Enterprise plans.
- [PII redaction](https://docs.firecrawl.dev/features/scrape#pii-redaction) removes personally identifiable information from scrape output.
- Data Processing Agreements (DPA), custom MSAs, and vendor security reviews for Enterprise customers.
- [SSO and SCIM](https://docs.firecrawl.dev/features/sso): SAML and OIDC single sign-on (Okta, Entra ID, Google Workspace, and more) and SCIM directory sync.
- Access controls: static IP allowlisting, [IP restrictions](https://docs.firecrawl.dev/features/ip-restrictions), and [key restrictions](https://docs.firecrawl.dev/features/key-restrictions) per API key.
- US data residency.
- Scale: custom and reserved concurrency, and credits pooled across teams in one organization.
- Buy through [AWS Marketplace](https://www.firecrawl.dev/integrations/aws-marketplace) or [Google Cloud Marketplace](https://www.firecrawl.dev/integrations/google-cloud-marketplace).

## Integrations

- [Integrations](https://www.firecrawl.dev/integrations): Native integrations with LlamaIndex, LangChain, Claude Code, Cursor, n8n, Make, Zapier, and Stripe Projects.
- [LangGraph](https://www.firecrawl.dev/integrations/langgraph): Add web search to a LangGraph agent with the FirecrawlSearch tool and a ToolNode, with Python code.
- [LangChain](https://www.firecrawl.dev/integrations/langchain): The official langchain-firecrawl package. FirecrawlSearch and FirecrawlScrape agent tools for create_agent, plus a document loader with a search mode.
- [LlamaIndex](https://www.firecrawl.dev/integrations/llamaindex): Give a LlamaIndex FunctionAgent web search with Firecrawl, or load search results as documents with FireCrawlWebReader.
- [OpenAI](https://www.firecrawl.dev/integrations/openai): Define Firecrawl search as an OpenAI function calling tool (Responses API) or as a function_tool in the OpenAI Agents SDK.
- [Dify](https://www.firecrawl.dev/integrations/workflow-automation/dify): Add web search to Dify agents with the official Firecrawl plugin (Search, Scrape, Crawl, Map, Monitor actions). Covers the Flowise Firecrawl block too.
- [n8n](https://www.firecrawl.dev/integrations/n8n): The Firecrawl node's Search Web operation for n8n workflows, and Firecrawl as a tool on the n8n AI Agent node.
- [Firecrawl in ChatGPT](https://www.firecrawl.dev/integrations/chatgpt): The official Firecrawl plugin for ChatGPT and Codex: search, scrape, map, crawl and interact from the chat, including summarizing every page on a site and reading JavaScript-heavy pages.
- [Firecrawl in Claude](https://www.firecrawl.dev/integrations/claude): The official Firecrawl connector for Claude: web search, scraping into Markdown or JSON fields, research papers and the Firecrawl Developer Index, including extracting structured data from a list of URLs and adding sources to Claude's Research mode.

## Use Cases

- [Use Cases](https://www.firecrawl.dev/use-cases): Common production use cases — AI MCPs, autonomous agents, SEO analysis, e-commerce intelligence, financial research, and lead enrichment.
- [Government and public records data](https://www.firecrawl.dev/use-cases/government-data): SAM.gov contract opportunities, Grants.gov funding, CourtListener case law, Federal Register rules through the Government Index, and state business registries for AI agents, from 120+ official sources in Firecrawl Alexandria.
- [Fantasy football start/sit](https://www.firecrawl.dev/alexandria/fantasy): Live fantasy football rankings, projections and lineup advice from six expert sources, built on Alexandria providers.
- [Fireround: startup funding news](https://www.firecrawl.dev/tools/fireround): Who just raised: the newest startup funding rounds with their amounts, stages and lead investors, and the last 30 days in numbers, live from the Fireround provider on Alexandria.
- [Prompts to try in ChatGPT and Claude](https://www.firecrawl.dev/prompts): Ready-to-copy prompts for ChatGPT, Claude and MCP clients, each with the answer it got back: ticket prices, prediction market odds, fantasy projections, open restaurant tables, flood zones and more, using Firecrawl Alexandria. Each prompt has its own page at `https://www.firecrawl.dev/prompts/<slug>`.

## Alternatives

- [Alternatives](https://www.firecrawl.dev/alternatives): Comparison pages vs Bright Data, Apify, Playwright, SerpAPI, and other web data tools.

## Customers

- [Customer Stories](https://www.firecrawl.dev/blog/category/customer-stories): How teams like Zapier, Stanford University, DoorDash, etc. use Firecrawl in production.

## Blog

- [Blog](https://www.firecrawl.dev/blog): Tutorials, guides, and product updates on web search, scrape, crawl, and building AI agent workflows.
- [How to add web search to an AI app](https://www.firecrawl.dev/blog/add-web-search-to-ai-app): Python and TypeScript code for Firecrawl Search, a chatbot tool-calling loop, web search for local LLMs on Ollama, and citing sources from search results.

## Changelog

- [Changelog](https://www.firecrawl.dev/changelog): Latest product updates, new endpoint launches, and engine upgrades. Every entry has its own markdown page; the full list is at https://www.firecrawl.dev/changelog.md.
- [The Company Enrichment Benchmark](https://www.firecrawl.dev/changelog/company-enrichment-benchmark.md): We tested the leading company enrichment providers on hundreds of U.S. companies to see who delivers accurate data and where information is missing. (October 21, 2026)
- [Free People Data for ChatGPT and Claude](https://www.firecrawl.dev/changelog/people-data-relaunch.md): Give your AI agents access to 270M+ company and people records in Alexandria, with 1,000 free credits a month through the Firecrawl plugin. (October 20, 2026)
- [Firecrawl for Google Cloud](https://www.firecrawl.dev/changelog/google-cloud-launch.md): We're partnering with Google Cloud to give Gemini and ADK agents data from the web and beyond, available on Google Cloud Marketplace. (October 19, 2026)
- [Introducing Fireround](https://www.firecrawl.dev/changelog/fireround.md): Fireround is a new company funding data provider built by Firecrawl. Follow new rounds and research investors in ChatGPT and Claude through Alexandria. (October 15, 2026)
- [Introducing the Marketing Data Pack in Alexandria](https://www.firecrawl.dev/changelog/alexandria-marketing-data-pack.md): Uncover what gets traffic and attention, shape your SEO and GEO strategy, and create content and visuals with better references in ChatGPT or Claude. (October 13, 2026)
- [Introducing Universal Scrape](https://www.firecrawl.dev/changelog/universal-scrape.md): Web pages, files and a growing set of Alexandria providers, all with one Firecrawl API. (October 8, 2026)
- [Fantasy sports data is live in Alexandria](https://www.firecrawl.dev/changelog/alexandria-fantasy-sports.md): Use fantasy rankings, projections, sports betting odds and live news in ChatGPT or Claude to research your next lineup with Firecrawl. (October 6, 2026)
- [People and company enrichment in Alexandria](https://www.firecrawl.dev/changelog/alexandria-people-enrichment.md): Apollo, FullEnrich, and Data Legion give your agents people search, work email lookup, and company enrichment through Firecrawl. (October 1, 2026)

## Legal

- [Terms of Service](https://www.firecrawl.dev/terms-of-service): Firecrawl's terms of service.
- [Privacy Policy](https://www.firecrawl.dev/privacy-policy): Data collection and usage policy.
- [Contributor License Agreement](https://www.firecrawl.dev/cla): CLA for open-source contributors.

## Optional

- [Glossary](https://www.firecrawl.dev/glossary): Definitions of web data API concepts — scraping, crawling, search, extraction, and browser automation.
- [Tools](https://www.firecrawl.dev/tools): Free web extraction tools — URL extractor, URL-to-JSON converter, article summarizer, website-to-markdown, and website-to-text.