Rust Agent Quickstart

Canonical Firecrawl Rust quickstart for external agents using search, scrape, and interact.

Firecrawl Rust Agent Quickstart

Canonical quickstart for external agents. Generated from SDK source (firecrawl crate) and the v2 OpenAPI spec. Method names and parameters match the SDK public API.

Install

cargo add firecrawl

Crate: firecrawl on crates.io.

Authenticate

use firecrawl::Client;

let client = Client::new("fc-your-api-key")?;

// Self-hosted:
// let client = Client::new_selfhosted("http://localhost:3002", Some("fc-your-api-key"))?;

Client::new(api_key) connects to https://api.firecrawl.dev. Client::new_selfhosted(api_url, api_key) connects to a self-hosted instance. An empty key falls back to the keyless free tier.

When To Use What

• search: use when you start with a query and need discovery.
• scrape: use when you already have a URL and want page content.
• interact: use when the page needs clicks, forms, or post-scrape browser actions. Requires a scrapeId from a prior scrape.

Search

Why use it

Discover relevant pages from a query, then pick URLs to scrape or interact with. Constrain results to a site with site: in the query.

Preferred SDK method

client.search(query, options) → Result<SearchResponse, FirecrawlError>

Example

use firecrawl::Client;

let results = client
    .search("site:docs.firecrawl.dev webhook retries", None)
    .await?;

if let Some(web) = results.data.web {
    for item in web {
        println!("{:?}", item);
    }
}

Results are in results.data.web, results.data.news, results.data.images.

Parameters

Parameter	Type	Description
query	impl AsRef<str>	Search query. Use site:example.com to scope to a domain.
options.sources	Vec<SearchSource>	Sources: Web, News, Images.
options.categories	Vec<SearchCategory>	Filter: Github, Research, Pdf.
options.include_domains	Vec<String>	Restrict results to these domains.
options.exclude_domains	Vec<String>	Exclude results from these domains.
options.limit	u32	Max results. Default: 5, max: 20.
options.tbs	String	Time-based filter (e.g. "qdr:d", "qdr:w").
options.location	String	Localized search results.
options.ignore_invalid_urls	bool	Drop invalid URLs.
options.timeout	u32	Request timeout in milliseconds.
options.highlights	bool	Generate query-relevant highlights. Default: true.
options.scrape_options	ScrapeOptions	Scrape each search result (see Scrape parameters).
options.integration	String	Integration identifier.

Scrape

Why use it

Get structured content from a URL in one or more formats.

Preferred SDK method

client.scrape(url, options) → Result<Document, FirecrawlError>

Example

use firecrawl::{Client, ScrapeOptions, Format};

let doc = client
    .scrape("https://docs.firecrawl.dev", ScrapeOptions {
        formats: Some(vec![Format::Markdown]),
        ..Default::default()
    })
    .await?;

println!("{:?}", doc.markdown);

Parameters

Parameter	Type	Description
url	impl AsRef<str>	URL to scrape.
options.formats	Vec<Format>	Output formats: Markdown, Html, RawHtml, Links, Images, Screenshot, Summary, ChangeTracking, Json, Attributes, Branding, Product, Menu, Audio, Video. Also Question(QuestionFormat), Highlights(HighlightsFormat).
options.headers	HashMap<String, String>	Custom HTTP headers.
options.include_tags	Vec<String>	HTML tags to include.
options.exclude_tags	Vec<String>	HTML tags to exclude.
options.only_main_content	bool	Strip nav, footer, and boilerplate.
options.timeout	u32	Timeout in milliseconds.
options.wait_for	u32	Wait for page render (milliseconds).
options.mobile	bool	Mobile viewport.
options.parsers	Vec<ParserConfig>	File parsers. PDF: ParserConfig::Pdf { parser_type, max_pages, pages, blocks, page_markers }.
options.actions	Vec<Action>	Pre-scrape actions: Wait, Click, Write, Press, Scroll, Scrape, Screenshot, ExecuteJavascript, Pdf.
options.location	LocationConfig	Geo config: country, languages.
options.skip_tls_verification	bool	Skip TLS verification.
options.remove_base64_images	bool	Drop base64 images from markdown.
options.fast_mode	bool	Faster scrapes, reduced fidelity.
options.block_ads	bool	Block ads and cookie popups.
options.proxy	ProxyType	Proxy: Basic, Stealth, Enhanced, Auto.
options.max_age	u32	Max age of cached content (milliseconds).
options.min_age	u32	Min age of cached content (milliseconds).
options.store_in_cache	bool	Cache the result.
options.profile	ProfileConfig	Persistent browser profile: name, save_changes.
options.json_options	JsonOptions	JSON extraction: schema, system_prompt, prompt.
options.screenshot_options	ScreenshotOptions	Screenshot: full_page, quality, viewport.
options.change_tracking_options	ChangeTrackingOptions	Change tracking: modes (GitDiff, Json), schema, prompt, tag.
options.attribute_selectors	Vec<AttributeSelector>	Attribute extraction: selector, attribute.

Interact

Why use it

Control the browser session tied to a prior scrape. Use for clicks, form fills, code execution, or natural-language instructions.

Preferred SDK method

client.interact(job_id, options) → Result<ScrapeExecuteResponse, FirecrawlError>

At least one of code or prompt must be non-empty; otherwise returns FirecrawlError::Misuse.

Example

use firecrawl::{Client, ScrapeOptions, ScrapeExecuteOptions, Format};

let doc = client
    .scrape("https://example.com", ScrapeOptions {
        formats: Some(vec![Format::Markdown]),
        ..Default::default()
    })
    .await?;

let job_id = doc.metadata
    .as_ref()
    .and_then(|m| m.scrape_id.as_ref())
    .expect("Missing scrapeId");

let result = client
    .interact(
        job_id,
        ScrapeExecuteOptions {
            prompt: Some("Click the pricing tab and summarize the plans.".to_string()),
            ..Default::default()
        },
    )
    .await?;

// When done:
client.stop_interaction(job_id).await?;

Parameters

Parameter	Type	Description
job_id	impl AsRef<str>	Scrape job ID from document.metadata.scrape_id.
options.code	Option<String>	Code to execute. At least one of code or prompt required.
options.prompt	Option<String>	Natural-language instruction. At least one of code or prompt required.
options.language	ScrapeExecuteLanguage	Runtime: Python, Node, Bash. Default: Node.
options.timeout	u32	Execution timeout in seconds.

Stop the session with client.stop_interaction(job_id).

Notes

• Deprecated aliases: scrape_execute → interact, stop_interactive_browser / delete_scrape_browser → stop_interaction.
• All types are exported at crate root: use firecrawl::Client.
• ScrapeOptions has dedicated sub-option structs: json_options, screenshot_options, change_tracking_options.
• search_and_scrape(query, limit) is a convenience that calls search with default scrape options and returns Vec<Document>.

Source Of Truth

• firecrawl/apps/rust-sdk/Cargo.toml
• firecrawl/apps/rust-sdk/src/client.rs
• firecrawl/apps/rust-sdk/src/scrape.rs
• firecrawl/apps/rust-sdk/src/search.rs
• firecrawl-docs/api-reference/v2-openapi.json