scrapfly

{
  "$schema": "https://a2a-protocol.org/schemas/v0.3/agent-card.json",
  "protocolVersion": "0.3",
  "name": "scrapfly",
  "description": "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.",
  "version": "1.0.0",
  "url": "https://mcp.scrapfly.io",
  "preferredTransport": "JSONRPC",
  "documentationUrl": "https://scrapfly.io/docs",
  "iconUrl": "https://scrapfly.io/img/logo.png",
  "provider": {
    "organization": "Scrapfly",
    "url": "https://scrapfly.io",
    "legalName": "Joam Intelligence LLC"
  },
  "capabilities": {
    "streaming": true,
    "pushNotifications": true,
    "stateTransitionHistory": false
  },
  "defaultInputModes": [
    "text/plain",
    "application/json"
  ],
  "defaultOutputModes": [
    "application/json",
    "text/markdown",
    "text/html",
    "image/png"
  ],
  "skills": [
    {
      "id": "scrape_url",
      "name": "Scrape a URL",
      "description": "Fetch a single URL through Scrapfly's managed proxy and anti-bot bypass infrastructure, returning the full HTML response or rendered DOM.",
      "tags": [
        "scraping",
        "http",
        "anti-bot",
        "proxy"
      ],
      "examples": [
        "Fetch the HTML of https://example.com",
        "Scrape a Cloudflare-protected page using residential proxies in Germany",
        "Get the rendered DOM of a JavaScript-heavy SPA"
      ],
      "inputModes": [
        "text/plain",
        "application/json"
      ],
      "outputModes": [
        "text/html",
        "text/markdown",
        "application/json"
      ]
    },
    {
      "id": "extract_data",
      "name": "Extract structured data",
      "description": "Extract typed structured data from a web page using a JSON schema or natural-language prompt; LLM-grounded with citations back to source HTML.",
      "tags": [
        "extraction",
        "structured-data",
        "llm",
        "schema"
      ],
      "examples": [
        "Extract product name, price, and availability from a product page",
        "Pull the author, publish date, and body from an article",
        "Get all reviews from a Yelp business page as JSON"
      ],
      "inputModes": [
        "application/json"
      ],
      "outputModes": [
        "application/json"
      ]
    },
    {
      "id": "take_screenshot",
      "name": "Take a screenshot",
      "description": "Capture a full-page, viewport, or element-level screenshot of a live URL.",
      "tags": [
        "screenshot",
        "rendering",
        "visual"
      ],
      "examples": [
        "Take a full-page screenshot of https://example.com",
        "Screenshot just the .product-card element",
        "Render a page as PDF"
      ],
      "inputModes": [
        "text/plain",
        "application/json"
      ],
      "outputModes": [
        "image/png",
        "image/jpeg",
        "application/pdf"
      ]
    },
    {
      "id": "crawl_site",
      "name": "Crawl a site",
      "description": "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.",
      "tags": [
        "crawler",
        "site-traversal",
        "bulk"
      ],
      "examples": [
        "Crawl all product pages on https://shop.example.com up to 10,000 URLs",
        "Crawl a site, scrape each page with anti-bot, deliver via webhook"
      ],
      "inputModes": [
        "application/json"
      ],
      "outputModes": [
        "application/json"
      ]
    },
    {
      "id": "browser_action",
      "name": "Cloud Browser action",
      "description": "Drive a remote Chromium session via Playwright, Puppeteer, Selenium, or raw CDP. Supports multi-step flows: login, click, type, evaluate JavaScript.",
      "tags": [
        "browser",
        "automation",
        "playwright",
        "puppeteer",
        "cdp"
      ],
      "examples": [
        "Log into a site and download a CSV from the dashboard",
        "Solve a multi-step search form and screenshot the results",
        "Run a custom JavaScript scenario and return the page state"
      ],
      "inputModes": [
        "application/json"
      ],
      "outputModes": [
        "application/json",
        "image/png"
      ]
    }
  ],
  "securitySchemes": {
    "oauth2": {
      "type": "oauth2",
      "flows": {
        "authorizationCode": {
          "authorizationUrl": "https://mcp.scrapfly.io/oauth/authorize",
          "tokenUrl": "https://mcp.scrapfly.io/oauth/token",
          "scopes": {
            "scrape": "Issue scrape requests",
            "browser": "Drive a Cloud Browser session",
            "screenshot": "Take screenshots",
            "extract": "Run structured-data extraction",
            "crawler": "Manage and execute site crawls"
          }
        }
      }
    },
    "apiKey": {
      "type": "apiKey",
      "in": "query",
      "name": "key",
      "description": "Long-lived API key (scp-live-{32-hex}) issued from https://scrapfly.io/dashboard"
    }
  },
  "security": [
    {
      "oauth2": [
        "scrape",
        "browser",
        "screenshot",
        "extract",
        "crawler"
      ]
    },
    {
      "apiKey": []
    }
  ],
  "supportsAuthenticatedExtendedCard": false,
  "additionalInterfaces": [
    {
      "url": "https://api.scrapfly.io",
      "transport": "HTTP",
      "description": "Direct REST API (Scrape, Screenshot, Extraction, Crawler) \u2014 language-agnostic, key-authenticated"
    },
    {
      "url": "https://browser.scrapfly.io",
      "transport": "WebSocket",
      "description": "Cloud Browser CDP / Playwright / Puppeteer / Selenium connect URL"
    }
  ]
}