MrScraper MCP connector for AI agents

CALL ANY TOOL

3 tools for web scraping in MrScraper: fetch a page as HTML, Markdown, or a screenshot, search Google with parsed JSON results, and check account usage and remaining tokens.

mrscrapermcp_scraperapi

Scraperapi

Retrieves a known page through MrScraper's Scraper API as HTML, Markdown, a screenshot, or a combination. Matches the Python SDK's scraper_api options. Omit browser_rendering for automatic browser fallback; screenshot=true always enables it. super enables real-device routing independently. home_page maps to warmStart. Proxy, cookie, target-header, retry, and timeout options control page loading. Returns status_code, data, and sanitized headers.

Parameters

Name

Type

Required

Description

url

string

Required

Required absolute HTTP or HTTPS page URL.

block_resources

boolean

Optional

Block images, CSS, and fonts during loading. Default: `false`.

browser_rendering

boolean

Optional

True forces browser rendering, false disables it; omit or use null for automatic fallback.

bypass_proxy

boolean

Optional

Enable the API's proxy-bypass/resource-blocking behavior. Default: `false`.

cookie_jar

string

Optional

Cookie configuration string, such as domain=example.com&country=us&max_used=100&max_age=50m.

discard_token_secret

string

Optional

Optional value for the x-discard-token-secret upstream header. Default: ``.

geo_code

string

Optional

Proxy geolocation country code, such as US, ID, or SG. Default: `US`.

headers

object

Optional

Target page request headers as an object or JSON string.

home_page

boolean

Optional

Visit the site's root before the target URL; sent as warmStart=true. Default: `false`.

html

boolean

Optional

Request HTML page content. Default: `true`.

markdown

boolean

Optional

Request Markdown page content. Default: `false`.

max_retries

integer

Optional

Maximum Web Unblocker retries; 0 disables retries. Default: `3`.

proxy

string

Optional

Custom proxy in username:password@host:port form.

proxy_country

string

Optional

Compatibility country option sent as proxyCountry.

screenshot

boolean

Optional

Capture a screenshot; always enables browser rendering. Default: `false`.

stream

boolean

Optional

Ask the API to stream; the MCP server buffers the response into the normal envelope.

super

boolean

Optional

Use real-device routing independently of browser rendering. Default: `false`.

timeout

integer

Optional

Page timeout in seconds (1-300); transport allows 30 additional seconds. Default: `120`.

token_cap

integer

Optional

Optional nonnegative retry-token budget.

use_proxy

boolean

Optional

Allow the service to use a configured proxy. Default: `true`.

wait_for_selector

string

Optional

CSS selector to wait for before returning page content.

mrscrapermcp_status

Status

mrscrapermcp_websearch

Websearch

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);

// MrScraper tools scoped to this user
const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["mrscrapermcp"], toolNames: [
    "mrscrapermcp_status",
    "mrscrapermcp_websearch",
    "mrscrapermcp_scraperapi"] },
  pageSize: 100,
});

const agent = createReactAgent({ llm, tools });
await agent.invoke({ messages: [{ role: "user", content: "Search Google for agent auth platforms and scrape the top result as Markdown" }] });

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: ["mrscrapermcp"] }, pageSize: 100,
});

const res = await openai.chat.completions.create({
  model: "gpt-5",
  messages: [{ role: "user", content: "Search Google for agent auth platforms and scrape the top result as Markdown" }],
  tools,
});

// Execute the tool call with the user's vaulted MrScraper OAuth 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: ["mrscrapermcp"] }, pageSize: 100,
});

const msg = await anthropic.messages.create({
  model: "claude-sonnet-5",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Search Google for agent auth platforms and scrape the top result as Markdown" }],
  tools,
});

// Tool call runs with the user's vaulted MrScraper OAuth 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: ["mrscrapermcp"] }, pageSize: 100,
});

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

await agent.run("Search Google for agent auth platforms and scrape the top result as Markdown");

Try these prompts

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

Scrape pages

Copy the prompt

Copied

Get our competitor's pricing page as Markdown.

Copy the prompt

Copied

Take a screenshot of the homepage at acme.com.

Copy the prompt

Copied

Fetch this product page with browser rendering on.

Google search

Copy the prompt

Copied

Search Google for agent authentication platforms and return parsed results.

Copy the prompt

Copied

Search Google in Germany for CRM software and show page 2.

Copy the prompt

Copied

Run this Google search URL and list the top 10 results.

Account

Copy the prompt

Copied

How many MrScraper tokens do I have left?

Copy the prompt

Copied

What is my MrScraper rate limit?

Copy the prompt

Copied

Check my subscription status before a large scrape.

SEE HOW AUTH WORKS

Each user signs in to MrScraper once, and Scalekit stores and refreshes their tokens. Credentials stay vaulted, every call is scope checked, and every action is logged.

1

Authorize

Your user connects

MrScraper 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

MrScraper 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

MrScraper 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

MrScraper 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 AI and web automation 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.

Test other agents

See the same per-user auth pattern across other AI and web automation connectors.

GTM

Competitive intelligence briefing agent

Scan Gong calls for competitor mentions, match each one to its Notion battlecard, and DM every affected rep a single Slack digest.

SALES

Outbound prospecting agent

Search Apollo for ICP matches, rank them, draft personalised Gmail outreach, and log every send to Google Sheets.

Why Scalekit

Secure your agent's access. Connectors ship in minutes

01.

Shared tokens break per-user analytics

A shared MrScraper token looks fine in a demo. In production every scrape and search 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.

MrScraper 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 MrScraper as the user or through a shared service account?

As the user. Each user signs in to MrScraper once, and Scalekit stores and refreshes their tokens. Every scrape and search in your audit trail is attributed to that user, not a shared service account.

Where is the MrScraper 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 MrScraper?

Yes. All MrScraper tools only read: they fetch pages, run searches, and report account usage, and none changes anything in the account. Filter by tool name in listScopedTools to expose only what you want, for example mrscrapermcp_websearch without mrscrapermcp_scraperapi. Scalekit also enforces scope checks before every API call.

What happens when a user revokes MrScraper 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.

How does the agent see how much MrScraper quota is left?

mrscrapermcp_status returns the connected account's subscription status, token limit, token usage, remaining tokens, and rate limit. It takes no input, so the agent can call it before a large batch of requests.

MrScraper MCP server for AI agents

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