Scrapfly MCP connector for AI agents

Tools your research agent reaches for on Scrapfly, scoped per user.

CALL ANY TOOL

31 tools for web scraping with Scrapfly: scrape and screenshot URLs, unblock protected pages, check account credits, and click, fill, and navigate in cloud browser sessions.

scarpflymcp_browser_unblock

Browser unblock

Unblock a URL using a headless browser with anti-scraping protection. Returns the page content after bypassing bot detection.

Parameters

Name

Type

Required

Description

url

string

Required

Target URL to fetch or interact with.

country

string

Optional

Two-letter ISO 3166-1 alpha-2 country code for the proxy exit node (e.g. US, DE, FR).

timeout

integer

Optional

Server-side timeout in milliseconds. Use alongside rendering_wait for JS-heavy pages.

scarpflymcp_call_webmcp_tool

Call webmcp tool

scarpflymcp_check_if_blocked

Check if blocked

scarpflymcp_click

Click

scarpflymcp_cloud_browser_close

Close cloud browser

scarpflymcp_cloud_browser_downloads

Cloud browser downloads

scarpflymcp_cloud_browser_eval

Cloud browser eval

scarpflymcp_cloud_browser_navigate

Cloud browser navigate

scarpflymcp_cloud_browser_open

Open cloud browser

scarpflymcp_cloud_browser_performance

Cloud browser performance

scarpflymcp_cloud_browser_screenshot

Cloud browser screenshot

scarpflymcp_cloud_browser_sessions

Cloud browser sessions

scarpflymcp_drag

Drag

scarpflymcp_evaluate_script

Evaluate script

scarpflymcp_fill

Fill

scarpflymcp_get_page_url

Get page url

scarpflymcp_hover

Hover

scarpflymcp_info_account

Info account

scarpflymcp_info_api_key

Info api key

scarpflymcp_inspect_page

Inspect page

scarpflymcp_list_webmcp_tools

List webmcp tools

scarpflymcp_press_key

Press key

scarpflymcp_scraping_instruction_enhanced

Scraping instruction enhanced

scarpflymcp_screenshot

Screenshot

scarpflymcp_scroll

Scroll

scarpflymcp_select_option

Select option

scarpflymcp_take_screenshot

Take screenshot

scarpflymcp_take_snapshot

Take snapshot

scarpflymcp_type_text

Type text

scarpflymcp_web_get_page

Web get page

For more tools, view docs.

Build your Agent

Same auth pattern across LangChain, OpenAI, Anthropic, and Google ADK.

import { ScalekitClient } from "@scalekit-sdk/node";
import { createReactAgent } from "@langchain/langgraph/prebuilt";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

// Scrapfly MCP tools scoped to this user
const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["scarpflymcp"], toolNames: [
    "scarpflymcp_web_get_page",
    "scarpflymcp_web_scrape",
    "scarpflymcp_screenshot",
    "scarpflymcp_check_if_blocked"] },
  pageSize: 100,
});

const agent = createReactAgent({ llm, tools });
await agent.invoke({ messages: [{ role: "user", content: "Scrape acme.com/pricing and list each plan with its price" }] });

import OpenAI from "openai";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const openai = new OpenAI();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["scarpflymcp"] }, pageSize: 100,
});

const res = await openai.chat.completions.create({
  model: "gpt-5",
  messages: [{ role: "user", content: "Scrape acme.com/pricing and list each plan with its price" }],
  tools,
});

// Execute the tool call with the user's vaulted Scrapfly token
await sk.tools.executeTool(res.choices[0].message.tool_calls[0], "user_123");

import Anthropic from "@anthropic-ai/sdk";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const anthropic = new Anthropic();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["scarpflymcp"] }, pageSize: 100,
});

const msg = await anthropic.messages.create({
  model: "claude-sonnet-5",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Scrape acme.com/pricing and list each plan with its price" }],
  tools,
});

// Tool call runs with the user's vaulted Scrapfly token
await sk.tools.executeTool(msg.content, "user_123");

import { Agent } from "@google/adk/agents";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["scarpflymcp"] }, pageSize: 100,
});

const agent = new Agent({
  name: "research_agent",
  model: "gemini-2.5-pro",
  instruction: "Scrapfly MCP tools scoped to this user",
  tools,
});

await agent.run("Scrape acme.com/pricing and list each plan with its price");

Try these prompts

Copy any prompt into your agent. Each maps directly to a Scrapfly MCP tool. Click to copy, paste into your agent, done.

Scrape and fetch

Copy the prompt

Copied

Scrape acme.com/pricing and list each plan with its price.

Copy the prompt

Copied

Fetch this product page with JavaScript rendering and return the page content.

Copy the prompt

Copied

Check whether this URL returns a captcha or blocked page.

Screenshots and performance

Copy the prompt

Copied

Take a full-page screenshot of our homepage.

Copy the prompt

Copied

Screenshot the checkout page at 1280 by 800.

Copy the prompt

Copied

Get Core Web Vitals for the page open in my cloud browser session.

Cloud browser sessions

Copy the prompt

Copied

Open a cloud browser session on the login page and take a snapshot.

Copy the prompt

Copied

Fill the search box with running shoes and press Enter.

Copy the prompt

Copied

List my active cloud browser sessions and close the idle ones.

SEE HOW AUTH WORKS

Each user signs in to Scrapfly once; Scalekit stores and refreshes their tokens. Every call is scope checked, and every action is logged.

Authorize

Your user connects

Scarpfly MCP

once. We tie it to their identity and the meetings they approved — no shared bot account, no org-wide access

Who:

user ‘A’

when:

Once per user

access:

Limited to user

Store

Their

Scarpfly MCP

token lives in a vault scoped to them. User A's meetings are never reachable by an agent acting for user B, even on the same connection

vault:

encrypted

scope:

per-user

tokens:

auto-refreshed

Resolve

When your agent calls a

Scarpfly MCP

tool, we fetch the right token server-side. It never touches your agent, never appears in the LLM context, never shows up in your logs

speed:

~40ms

check:

before every call

seen by:

nobody

Audit

Every

Scarpfly MCP

tool call is logged — who triggered it, which meeting was fetched, what came back. 90 days of history, tied to the user who authorized it

history:

90 days

export:

SIEM-ready

logged:

every call

Test other agents

See the same per-user auth pattern across other web scraping and search connectors.

GTM and RevOps Teams

Competitive intelligence briefing agent

Scans Gong calls for competitor mentions, matches each one to its Notion battlecard, and DMs every affected rep a single Slack digest per cycle. Every call runs as the PMM who owns the briefing, never a shared bot.

GTM and RevOps Teams

Outbound prospecting agent

Searches Apollo for prospects matching your ICP, scores and ranks them, drafts personalized outreach in Gmail, and logs every send to Google Sheets. Mail goes out as the rep, not from a shared inbox.

GTM and RevOps Teams

Deal intelligence agent

Pulls recent Gong calls, scores deal risk with an LLM, cross-references the record in Attio, and DMs each owner their at-risk deals in Slack. Every read is scoped to that rep's own access.

Support and Ops Teams

Meeting prep

Pulls agenda, participant context, and open action items before every meeting.

Why Scalekit

Secure your agent's access. Connectors ship in minutes

01.

Shared tokens break per-user analytics

A shared Scrapfly token looks fine in a demo. In production every scrape looks like one service account, and you cannot tell which user triggered it. Scalekit resolves the credential of the actual user who triggered the agent, never a shared bot.

// shared token
audit → bot_service_account

// scalekit
audit → user_abc ✓

02.

Authentication is not authorization

03.

Multi-tenancy is architectural

04.

Scrapfly today. Ten connectors tomorrow.

“Our agents act across Salesforce, Gong, Google Drive, and more, on behalf of every customer. Scalekit behind the scenes meant we can keep adding tools without ever rebuilding how credentials or tool calling work.”

Venu Madhav Kattagoni

Head of Engineering / Von

FAQs

Frequently Asked Questions

Does the agent access Scrapfly as the user or through a shared account?

As the user. Each user signs in to Scrapfly once, and Scalekit stores and refreshes their tokens. Audit logs attribute every scrape and browser action to that user, not a shared service account.

Where is the Scarpfly OAuth token stored?

In Scalekit's managed AES-256 token vault, namespaced per tenant. Refresh is automatic. Revocation is a single dashboard action. Credentials never appear in prompts, logs, or LLM context.

Can I limit what the agent does in Scrapfly?

Yes. Filter by tool name in listScopedTools, for example only scarpflymcp_web_get_page and scarpflymcp_screenshot for a read-only research agent. Scalekit also enforces scope checks before every API call.

What happens when a user revokes Scrapfly access?

The connection is invalidated on the next tool call. Subsequent requests for that user fail closed with a clear error. Other users in the tenant remain unaffected. The event is logged for audit.

Can the agent interact with a page, not only scrape it?

Yes. scarpflymcp_cloud_browser_open starts a cloud browser session on a URL. scarpflymcp_take_snapshot returns element uids that scarpflymcp_click, scarpflymcp_fill, and scarpflymcp_select_option act on, and scarpflymcp_cloud_browser_close ends the session.