ZenRows MCP connector for AI agents

CALL ANY TOOL

Scrape any URL with anti-bot bypass, render JavaScript-heavy sites, and automate cloud browsers. Same toolkit, every framework, no auth plumbing.

zenrows_scrape

Scrape URL

Scrape a URL with ZenRows' anti-bot bypass, proxy rotation, and optional JavaScript rendering.

Parameters

Name

Type

Required

Description

url

string

Required

URL to scrape

js_render

boolean

Optional

Enable JavaScript rendering (default false)

premium_proxy

boolean

Optional

Use premium residential proxies

response_type

string

Optional

Response type: html, markdown, text

zenrows_js_render

Render JS site

zenrows_screenshot

Take screenshot

zenrows_extraction_run

Run extraction

zenrows_browser_session

Start browser session

Build your Agent

Drop the toolkit in, point it at the user, and your agent can scrape and automate via ZenRows from the first run.

import { ScalekitClient } from "@scalekit-sdk/node";
import { DynamicStructuredTool } from "@langchain/core/tools";
import { createReactAgent } from "@langchain/langgraph/prebuilt";
import { z } from "zod";

const sk = new ScalekitClient(envUrl, clientId, clientSecret);

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["zenrowsmcp"], toolNames: ["zenrows_scrape", "zenrows_js_render", "zenrows_screenshot"] },
  pageSize: 100,
});

const lcTools = tools.map((t) => new DynamicStructuredTool({
  name: t.tool.definition.name,
  description: t.tool.definition.description,
  schema: z.object({}).passthrough(),
  func: async (args) => {
    const { data } = await sk.tools.executeTool({
      toolName: t.tool.definition.name,
      identifier: "user_123",
      params: args,
    });
    return JSON.stringify(data);
  },
}));

const agent = createReactAgent({ llm, tools: lcTools });

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

const sk = new ScalekitClient(envUrl, clientId, clientSecret);
const openai = new OpenAI();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["zenrowsmcp"], toolNames: ["zenrows_scrape", "zenrows_js_render", "zenrows_screenshot"] },
  pageSize: 100,
});

const llmTools = tools.map((t) => ({
  type: "function",
  function: {
    name: t.tool.definition.name,
    description: t.tool.definition.description,
    parameters: t.tool.definition.input_schema,
  },
}));

const resp = await openai.responses.create({
  model: "gpt-4o", input: prompt, tools: llmTools,
});

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

const sk = new ScalekitClient(envUrl, clientId, clientSecret);
const anthropic = new Anthropic();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["zenrowsmcp"], toolNames: ["zenrows_scrape", "zenrows_js_render", "zenrows_screenshot"] },
  pageSize: 100,
});

const llmTools = tools.map((t) => ({
  name: t.tool.definition.name,
  description: t.tool.definition.description,
  input_schema: t.tool.definition.input_schema,
}));

const msg = await anthropic.messages.create({
  model: "claude-sonnet-4-6", max_tokens: 1024,
  tools: llmTools,
  messages: [{ role: "user", content: prompt }],
});

import { Agent } from "@google/adk/agents";
import {
  MCPToolset, StreamableHTTPConnectionParams,
} from "@google/adk/tools/mcp";

const toolset = new MCPToolset({
  connectionParams: new StreamableHTTPConnectionParams({
    url: "https://mcp.scalekit.com/zenrowsmcp",
    headers: { Authorization: `Bearer ${userScopedToken}` },
  }),
});

const agent = new Agent({
  name: "agent", model: "gemini-2.0-flash",
  tools: await toolset.getTools(),
});

Try these prompts

Paste any prompt into your research agent to start scraping web content via ZenRows.

Scrape & extract

Copy the prompt

Copied

Scrape [URL] and return the page content as markdown.

Copy the prompt

Copied

Extract all [data type] from [URL] with JavaScript rendering.

Copy the prompt

Copied

Take a full-page screenshot of [URL].

Research

Copy the prompt

Copied

Scrape the pricing page at [URL] and list all plans and prices.

Copy the prompt

Copied

Get structured product data from [e-commerce URL] using a custom schema.

Copy the prompt

Copied

Start a browser session and navigate through [multi-step workflow] on [URL].

SEE HOW AUTH WORKS

Users authorize ZenRows once. Their credentials stay vaulted, every scrape job runs under their account quota, and every call is logged.

1

Authorize

Your user connects

ZenRows 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

2

Store

Their

ZenRows 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

3

Resolve

When your agent calls a

ZenRows 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

4

Audit

Every

ZenRows 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

Same per-user auth pattern across other developer tool and automation connectors.

No items found.

Why Scalekit

Secure your agent's access. Connectors ship in minutes

Other connector libraries treat auth as a demo afterthought. Scalekit starts with user identity, scope enforcement, and audit.

01.

Shared tokens break per-user analytics

A shared token looks fine in a demo. In production every call looks like a service account. Scalekit resolves the real user credential so attribution, audit, and scope stay accurate.

// shared token
 audit → bot_service_account
 user_filter → broken

 // scalekit
 audit → user_abc
 scope → enforced ✓

02.

Authentication is not authorization

03.

Multi-tenancy is architectural

04.

ZenRows MCP today. Others 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 use a shared ZenRows account or per-user accounts?

Per-user. Each developer's ZenRows credentials are vaulted under their identity. Scrape quota is tracked per user.

Where are ZenRows credentials stored?

In Scalekit's AES-256 vault, namespaced per tenant. Credentials resolve at request time and never appear in prompts.

Can I limit the agent to specific scraping operations?

Yes. Use listScopedTools to allow basic URL scraping without granting JS rendering or browser session creation.

What happens when a user's ZenRows credentials are revoked?

The next scrape call fails closed for that user. Other users remain unaffected. Revocation is logged.

Does this handle CAPTCHAs and bot detection?

Yes. ZenRows' anti-bot bypass handles CAPTCHAs, Cloudflare protection, and fingerprint detection at the infrastructure level.

ZenRows MCP

Tools your agent reaches for on ZenRows MCP, scoped per user.