# Introduction

> Search the web, scrape any page, and interact with it, all through one API.

import SearchPython from "/snippets/v2/search/base/python.mdx";
import SearchNode from "/snippets/v2/search/base/js.mdx";
import SearchCURL from "/snippets/v2/search/base/curl.mdx";
import SearchCLI from "/snippets/v2/search/base/cli.mdx";
import SearchResponse from "/snippets/v2/search/base/output.mdx";
import ScrapePython from "/snippets/v2/scrape/base/python.mdx";
import ScrapeNode from "/snippets/v2/scrape/base/js.mdx";
import ScrapeCURL from "/snippets/v2/scrape/base/curl.mdx";
import ScrapeCLI from "/snippets/v2/scrape/base/cli.mdx";
import ScrapeResponse from "/snippets/v2/scrape/base/output.mdx";
import InteractPython from "/snippets/v2/interact/quickstart/python.mdx";
import InteractNode from "/snippets/v2/interact/quickstart/js.mdx";
import InteractCURL from "/snippets/v2/interact/quickstart/curl.mdx";
import InteractCLI from "/snippets/v2/interact/quickstart/cli.mdx";
import InteractResponse from "/snippets/v2/interact/response/output.mdx";
import {
  AgentSetupButton,
  McpClientSelector,
} from "/snippets/shared/agent-first-onboarding.jsx";
import GeneralFeedbackCTA from "/snippets/general-feedback-cta.mdx";

## Get started

Connect over Streamable HTTP. The keyless server URL (Search, Scrape, and Parse; no credential required) is `https://mcp.firecrawl.dev/v2/mcp`.

- Codex: `codex mcp add firecrawl --url https://mcp.firecrawl.dev/v2/mcp`
- Claude Code: `claude mcp add --transport http firecrawl https://mcp.firecrawl.dev/v2/mcp`
- Cursor or any JSON-config client: `{"mcpServers": {"firecrawl": {"url": "https://mcp.firecrawl.dev/v2/mcp"}}}`
- OpenCode (`opencode.json`): `{"mcp": {"firecrawl": {"type": "remote", "url": "https://mcp.firecrawl.dev/v2/mcp", "enabled": true}}}`
- ChatGPT or Claude.ai: use the native Firecrawl connector — [ChatGPT](https://chatgpt.com/plugins?q=firecrawl) or [Claude](https://claude.ai/directory/connectors/firecrawl).

Both setup paths and API-key setup: [MCP Get Started](/mcp-server.md), [For Agents](/mcp-server/keyless.md), and [For Humans](/mcp-server/oauth.md).

### Build directly with the API

Scrape your first page now. No account or API key is required for this request.

<ScrapeCURL />

Add an [API key](https://www.firecrawl.dev/app/api-keys) when you need higher limits. See the [Python SDK](/sdks/python), [Node SDK](/sdks/node), or [API reference](/api-reference/endpoint/scrape) to build it into your application.

## Other ways to get started

### Install the Firecrawl CLI

One command installs the Firecrawl CLI, authenticates in your browser, and adds skills to every detected coding agent.

```bash
npx -y firecrawl-cli@latest init --all --browser
```

<Note>
  Restart your coding agent after setup so it can discover the new skills. See
  [CLI](/sdks/cli) for the full setup.
</Note>

### Set up with an agent

Provide your agent with this Firecrawl setup prompt, or see [all MCP setup options](/mcp-server).

<AgentSetupButton />

<Note>
  **For AI agents:** Use [llms.txt](https://docs.firecrawl.dev/llms.txt) for an index of the documentation, or [llms-full.txt](https://docs.firecrawl.dev/llms-full.txt) for the full text.
</Note>

### Build and test directly

<CardGroup cols={2}>
  <Card
    title="Get your API key"
    icon="key"
    href="https://www.firecrawl.dev/app/api-keys"
  >
    Create a free account for direct API access and higher limits
  </Card>
  <Card
    title="Try it in the Playground"
    icon="play"
    href="https://www.firecrawl.dev/playground"
  >
    Test Firecrawl in the browser without writing code
  </Card>
</CardGroup>

---

## What can Firecrawl do?

<CardGroup cols={3}>
  <Card title="Search" icon="magnifying-glass" href="#search">
    Search the web and get full page content from results
  </Card>
  <Card title="Scrape" icon="file-lines" href="#scrape">
    Extract content from any URL as markdown, HTML, or structured JSON
  </Card>
  <Card title="Interact" icon="hand-pointer" href="#interact">
    Continue working with any scraped page: click, fill forms, extract dynamic
    content
  </Card>
</CardGroup>

### Why Firecrawl?

- **LLM-ready output**: Clean markdown, structured JSON, screenshots, and more.
- **Handles the hard stuff**: Proxies, anti-bot, JavaScript rendering, and dynamic content.
- **Reliable**: Built for production with high uptime and consistent results.
- **Fast**: Results in seconds, optimized for high throughput.
- **MCP Server**: Connect Firecrawl to any AI tool via the [Model Context Protocol](/mcp-server).

<GeneralFeedbackCTA src="docs-introduction" />

---

## Search

Search the web and get full page content from results in one call. See the [Search feature docs](/features/search) for all options.

<CodeGroup>

<SearchPython />
<SearchNode />
<SearchCURL />
<SearchCLI />

</CodeGroup>

<Accordion title="Response">

SDKs will return the data object directly. cURL will return the complete payload.

<SearchResponse />

</Accordion>

## Scrape

Scrape any URL and get its content in markdown, HTML, or other formats. See the [Scrape feature docs](/features/scrape) for all options.

<CodeGroup>

<ScrapePython />
<ScrapeNode />
<ScrapeCURL />
<ScrapeCLI />

</CodeGroup>

<Accordion title="Response">

SDKs will return the data object directly. cURL will return the payload exactly as shown below.

<ScrapeResponse />

</Accordion>

## Interact

Scrape a page, then keep working with it: click buttons, fill forms, extract dynamic content, or navigate deeper. Describe what you want in plain English or write code for full control. See the [Interact feature docs](/features/interact) for all options.

<CodeGroup>

<InteractPython />
<InteractNode />
<InteractCURL />
<InteractCLI />

</CodeGroup>

<Accordion title="Response">

<InteractResponse />

</Accordion>

---

## More capabilities

<CardGroup cols={2}>
  <Card title="Agent" icon="robot" href="/features/agent">
    Autonomous web data gathering powered by AI
  </Card>
  <Card title="Interact" icon="hand-pointer" href="/features/interact">
    Click, fill forms, extract dynamic content
  </Card>
  <Card title="Webhooks" icon="webhook" href="/webhooks">
    Async event delivery
  </Card>
  <Card title="Browser Sandbox" icon="browser" href="/features/browser">
    Managed browser sessions for interactive workflows
  </Card>
  <Card title="Parse" icon="file-magnifying-glass" href="/features/parse">
    Turn local PDFs, DOCX, XLSX, HTML, and more into Markdown or structured JSON
  </Card>
  <Card title="Map" icon="map" href="/features/map">
    Discover all URLs on a website
  </Card>
  <Card title="Crawl" icon="spider-web" href="/features/crawl">
    Recursively gather content from entire sites
  </Card>
</CardGroup>

---

## Resources

<CardGroup cols={2}>
  <Card title="API Reference" icon="code" href="/api-reference/v2-introduction">
    Complete API documentation with interactive examples
  </Card>
  <Card title="SDKs" icon="boxes-stacked" href="/sdks/overview">
    Python, Node.js, CLI, and community SDKs
  </Card>
  <Card
    title="Open Source"
    icon="github"
    href="/contributing/open-source-or-cloud"
  >
    Self-host Firecrawl or contribute to the project
  </Card>
  <Card
    title="Integrations"
    icon="puzzle-piece"
    href="/developer-guides/llm-sdks-and-frameworks/openai"
  >
    LangChain, LlamaIndex, OpenAI, and more
  </Card>
</CardGroup>