Apify MCP for AI agents | Bearer token connector

Tools your web data agent reaches for on Apify MCP, scoped per user.

CALL ANY TOOL

Run scrapers, fetch dataset items, manage key-value stores, and orchestrate browser actors.

apify_actors_list

List actors

List all Apify actors available to the user with metadata.

Parameters

Name

Type

Required

Description

offset

integer

Optional

Pagination offset

limit

integer

Optional

Max actors to return

apify_actor_run

Run actor

apify_run_get

Get run status

apify_dataset_items

Get dataset items

apify_keyvalue_get

Get KV store record

Build your Agent

Drop the toolkit in, point it at the user, and your web data agent can use Apify MCP from the first run.

Copied

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: ["apifymcp"], toolNames: ["apify_actors_list", "apify_actor_run", "apify_run_get"] },
  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 });

Copied

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: ["apifymcp"], toolNames: ["apify_actors_list", "apify_actor_run", "apify_run_get"] },
  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: ["apifymcp"], toolNames: ["apify_actors_list", "apify_actor_run", "apify_run_get"] },
  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 }],
});

Copied

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/apifymcp",
    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 agent to start using Apify MCP.

Search & runs

Copy the prompt

Copied

List all actors available in my account.

Copy the prompt

Copied

Show me the last 5 runs of [actor name].

Copy the prompt

Copied

Get the status of run [run_id].

Copy the prompt

Copied

What datasets did [actor name] produce this week?

Action & extraction

Copy the prompt

Copied

Run [actor name] with input: [URL].

Copy the prompt

Copied

Scrape [target URL] and save to a dataset.

Copy the prompt

Copied

Fetch all items from dataset [dataset_id].

Copy the prompt

Copied

Re-run actor [actor name] with the same input.

Pipeline & monitoring

Copy the prompt

Copied

Which actors have failed in the last 24 hours?

Copy the prompt

Copied

List runs that exceeded 60s today.

Copy the prompt

Copied

Get the total compute units used this month.

Copy the prompt

Copied

Stop all running actors in [namespace].

SEE HOW AUTH WORKS

Users authorize Apify MCP once. Their credentials stay vaulted, every call is checked, and every action is logged.

Authorize

Your user connects

Apify 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

Apify 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

Apify 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

Apify 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 web data agents and MCP connectors. Working code, live demos, fork what fits.

SALES

Outbound prospecting agent

Build targeted prospect lists with Apollo, enrich with firmographic data, and draft personalised outreach. Runs on a schedule.

Apollo

View agent

ENGINEERING

Engineering standup agent

Aggregate GitHub and GitLab activity, link to Jira, and post a daily standup digest to Slack. No async updates.

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.

Actor runs charged to the wrong account

A shared Apify token looks fine in a demo. In production, every Actor run or dataset fetched looks like it came from a service account. Audit logs break. Per-user scoping breaks. Scalekit resolves the credential of the actual user who triggered the agent, never a shared bot.

// shared bot token
token = "sk_apify-mcp_shared_xxx"
audit → bot_service_account
user_filter → broken

// scalekit · per-user
token = resolve(user_id)
audit → user_abc
scope → enforced ✓

02.

Authentication is not authorization

03.

Multi-tenancy is architectural

04.

Apify today. PhantomBuster, Exa, Brave 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

On this page

Tool and actions Framework Compatibility Starter Prompt Auth Lifecycle Try Other Agents Why Scalekit

Frequently Asked Questions

Does the agent access Apify MCP as the user or as a shared key?

As the user. Each workspace member authorizes once and Scalekit resolves their credential at request time. Audit logs attribute every action to that user, not a shared service account.

Where is the Apify MCP bearer token stored?

Can I limit what the agent is allowed to do in Apify MCP?

What happens when a user revokes Apify MCP access?

Can the agent run any actor in my Apify account?

Start in your coding agent

Up and running in one command

Install the Scalekit skill in your editor of choice. Connector, auth, tools, prompt, all wired up

Claude Code REPL

Copy Copied

/plugin marketplace add scalekit-inc/claude-code-authstack
/plugin install agentkit@scalekit-auth-stack

Cursor Code REPL

Copy Copied

# ~/.cursor/mcp.json
{
""mcpServers"": {
""apifymcp"": {
""url"": ""https://mcp.scalekit.com/apifymcp"",
""headers"": { ""Authorization"": ""Bearer $SCALEKIT_TOKEN"" }
}
}
}

Codex Code REPL

Copy Copied

# ~/.codex/config.toml
[mcp_servers.apifymcp]
url = ""https://mcp.scalekit.com/apifymcp""
auth_env = ""SCALEKIT_TOKEN""

Copilot Code REPL

Copy Copied

# .vscode/mcp.json
{
""servers"": {
""apifymcp"": {
""url"": ""https://mcp.scalekit.com/apifymcp"",
""type"": ""http""
}
}
}