A2A Agent Card · Scrapfly

scrapfly

Scrapfly is a managed web scraping and browser automation platform. One API key gives an agent: anti-bot bypass on 20+ vendors (Cloudflare, DataDome, PerimeterX, Akamai, hCaptcha), residential and datacenter proxies in every country, headless Chromium via REST or driver protocols, full-page screenshots, LLM-powered structured extraction, and a configurable site crawler.

Open the live agent card → Agent endpoint Scrapfly provider profile
✓ Conformant with A2A 1.0.0. This card passes every structural check in the A2A specification’s AgentCard object — a capabilities object, a declared protocolVersion, and a well-formed skills array.
Provider: Scrapfly Conformance: Conformant Protocol: 0.3 Transport: JSONRPC Version: 1.0.0 Host: scrapfly.io Skills: 5
Discovery

An A2A client finds this agent by fetching the well-known path on the provider's own host. That is what makes an agent card different from every other agent artifact in this catalog: it is provider-published by construction — it cannot be derived, generated, or reconstructed on a provider's behalf.

https://scrapfly.io/.well-known/agent-card.json
Interfaces
https://api.scrapfly.io · transport HTTP · protocol
https://browser.scrapfly.io · transport WebSocket · protocol
Skills (5)

Scrape a URL scrape_url

Fetch a single URL through Scrapfly's managed proxy and anti-bot bypass infrastructure, returning the full HTML response or rendered DOM.

scrapinghttpanti-botproxy

Extract structured data extract_data

Extract typed structured data from a web page using a JSON schema or natural-language prompt; LLM-grounded with citations back to source HTML.

extractionstructured-datallmschema

Take a screenshot take_screenshot

Capture a full-page, viewport, or element-level screenshot of a live URL.

screenshotrenderingvisual

Crawl a site crawl_site

Crawl an entire website with configurable budget, depth, URL patterns, and per-page scraping options. Results are streamed via webhook or pulled from a job queue.

crawlersite-traversalbulk

Cloud Browser action browser_action

Drive a remote Chromium session via Playwright, Puppeteer, Selenium, or raw CDP. Supports multi-step flows: login, click, type, evaluate JavaScript.

browserautomationplaywrightpuppeteercdp
Documentation
https://scrapfly.io/docs
Evidence. Fetched 2026-07-28 from https://scrapfly.io/.well-known/agent-card.json, HTTP 200. The body was saved verbatim and is the sole source for everything on this page — no field is inferred. View the captured card. Providers change what they serve; if this card has moved or changed shape, the provider profile carries the current state as of the last build.