Apify MCP connector
The Apify connector lets Claude, ChatGPT, Cursor and the Elaichi Agent find and run actors, read datasets and run logs, and manage tasks and schedules in Apify, with each person signed in as themselves and every call logged.
-
How it connects. Connects over OAuth. The credential goes into a vault nobody reads back.
-
One address. https://api.elaichi.ai/mcp, the same for every user.
-
Their own access. An agent never gets more than the person it acts for.
How to connect
How to connect Apify to Claude, ChatGPT or Cursor
Two steps, about a minute.
In Elaichi
Connect Apify once
-
Open Connections, choose Add connection, and pick Apify.
-
Optionally set Share with to give a team access, then press Connect.
-
Approve it in Apify. Apify's own window opens. Whoever approves it decides what this connection can reach.
The credential is vaulted. Nobody reads it back, not even the AI.
Add connection
Choose a connector.
In your AI client
Point it at one endpoint
Everyone in the organization uses the same address, and each person only ever reaches what their own account allows.
Apify MCP connector for Claude
-
1
Open Customize, then Connectors.
-
2
Press Add.
-
3
Name it, paste the MCP server URL, then Continue.
https://api.elaichi.ai/mcp -
4
Sign in and approve.
On Team and Enterprise, an Owner adds it once. Everyone else turns it on for themselves.
Apify MCP connector for ChatGPT
-
1
Open Plugins, then press the + button.
-
2
Name it and paste the endpoint into Server URL.
https://api.elaichi.ai/mcp -
3
Leave Authentication on OAuth, then tick the risk acknowledgement.
-
4
Press Create, then sign in and approve.
Works on the web today. The plugin directory lives at chatgpt.com/plugins.
Apify MCP connector for Cursor
-
1
Open
~/.cursor/mcp.json. -
2
Add the endpoint under
mcpServers.https://api.elaichi.ai/mcp -
3
Reload Cursor, then sign in and approve.
~/.cursor/mcp.json
{
"mcpServers": {
"elaichi": {
"url": "https://api.elaichi.ai/mcp"
}
}
}
Set up per machine, so repeat it on each computer you work from.
Connect Apify to any MCP client
-
1
Add the endpoint as a remote MCP server.
https://api.elaichi.ai/mcp -
2
Sign in and approve.
{
"mcpServers": {
"elaichi": {
"url": "https://api.elaichi.ai/mcp"
}
}
}
The Elaichi Agent already has these tools, with nothing to set up.
Use cases
What teams do with Apify through Elaichi
Every one of these runs inside the access the person already has, and lands in the same audit log.
-
Marketing
Pull competitor prices before the Monday meeting
Start the pricing actor you already use, wait for the run to finish, and read the dataset items back as a plain table. No one has to open Apify or export a file.
-
Sales
Build a prospect list from a scraped directory
Ask for the latest items from the directory scraper's dataset and have them summarized by region or industry. The list is ready to hand over before the first call of the day.
-
Data
Check what came back from last night's crawl
Look at the dataset schema, sample the first hundred items, and spot a broken field before anyone builds a report on it.
-
Research
Find the right actor for a new source
Search the Apify Store for an actor that covers a new website, read its details and the relevant docs, and try a small run to see what the output looks like.
-
Engineering
Set up a task and put it on a schedule
Create an actor task with the inputs your team settled on, publish it, and add a weekly schedule so the crawl runs without anyone remembering to start it.
-
Operations
Catch a runaway run before it burns credits
Ask which runs have been going longer than usual, read the log of the one that looks stuck, and abort it from the same conversation.
Try asking
- “Which actor runs failed last night and what did the logs say?”
- “Show me the first 50 items from the Google Maps scraper dataset.”
- “Create a weekly schedule for the competitor pricing task.”
Compare
Elaichi vs Zapier MCP vs Composio for Apify
All three can connect Apify to an AI assistant, and all three have admin controls. They differ in where access lives and how you pay.
| What to check | Elaichi | Zapier MCP | Composio |
|---|---|---|---|
| Where the AI connects |
One address for the whole organization.
https://api.elaichi.ai/mcp
|
A server per member, created at sign-in. | An MCP endpoint per team, or an SDK. |
| Control over Apify tools | Allow or restrict single Apify tools, per role or user. | App and action restrictions on the account. | Role permissions, down to the action. |
| Record of calls | One audit entry per Apify call. | A History tab of tool calls. | A log of every tool call. |
| Single sign-on | SAML or OIDC, plus SCIM, on Gold. | SAML on Enterprise. | SAML and OIDC on Enterprise. |
| Price | $15 per user per month. | 2 tasks per successful call. | Billed per tool call. |
Sources: Zapier MCP docs, security, usage; Composio docs, gateway, enterprise, pricing. Checked September 2026.
Longer take: Zapier MCP alternative and when you don't need an MCP gateway.
AI tools
Apify tools for your AI agents
27 tools are ready to call through Elaichi's MCP endpoint the moment you connect Apify, governed by the same roles, restrictions, and audit log as everything else in Elaichi. Apify builds and runs these tools.
No tools match your search.
See it in Elaichi
What connecting Apify gets you
6 screens from the product, each doing one job for your Apify account.
The agent
Ask about any actor run in plain language.
Check which scrapes finished overnight and pull the dataset items without opening Apify.
- actors
- runs
- datasets
- tasks
Ask Elaichi to work across your apps.
Which actor runs failed last night and what did the logs say?
Show me the first 50 items from the Google Maps scraper dataset.
Create a weekly schedule for the competitor pricing task.
Also runs in Claude, ChatGPT or Cursor
MCP clients
One endpoint brings Apify to every client.
Claude, ChatGPT and Cursor all reach Apify through one governed endpoint, no shared API key.
Copy the endpoint
Tool catalog
27 Apify tools, ready without writing code.
Actors, runs, datasets, key-value stores, tasks and schedules, covered with no custom code.
- Search actors
- Fetch actor details
- Call actor
- Search Apify docs
Toolboxes
Each team gets its own Apify toolbox.
Marketing runs scrapers, Data reads datasets, Engineering manages tasks, each from a scoped toolbox.
- Marketing
- Sales
- Data
- Research
Shared connections
Share one Apify connection, never the token.
Teammates start runs and read datasets through your connection without ever seeing a credential.
- Marketing
- Sales
- Data team
- Research
Audit log
Every Apify call lands in the log.
See who started a run, aborted it, or published a task, and exactly when.
- When
- Who
- What happened
- Type
Launching soon
From answering questions to doing the work
A person no longer has to ask. A trigger starts the work, inside the same permissions and the same audit log as everything else. Automations and live dashboards are launching soon, on the Black plan.
Automations
A schedule starts the scrape and the digest.
Dataset items are fetched, grouped, drafted into a digest, approved, then the follow-up run starts.
Apify digest
Run 418 · started 2 minutes ago · on behalf of Emily Carter
-
✓
Schedule
Every weekday at 8:00 AM
0.2s -
✓
Fetch actors
Apify
1.4s -
✓
Group by owner
Transform
0.1s -
✓
Draft the digest
Agent step
Ran with 4 tools, returned a structured summary
6.2s -
Approve the digest
Needs approval
Assigned to Michael Brennan
Approve Deny -
Post the digest
Apify
Queued
Collections and dashboards
Apify health, computed on a schedule, no prompt.
Runs, failures, dataset items and compute per team, refreshed hourly with no model involved.
Apify health
Refreshed 4 minutes ago · every 15 minutes · from the actors collection
Actors
1,284 ↓ 12%
Runs
96 ↓ 8%
Needs attention
3 ↑ 2
Updated this week
412 ↑ 9%
Actors created
Last 14 days
By team
Share of activity
Marketing 34%
Sales 27%
Data team 21%
Research 18%
FAQ
Frequently asked questions
How do I connect Apify to Claude?
Connect Apify in Elaichi first: you sign in with your Apify account over OAuth and approve access, with no OAuth application to register and no client ID or secret to generate. Then in Claude open Customize, then Connectors, then Add, and paste https://api.elaichi.ai/mcp. Claude asks you to sign in to Elaichi, and from then on Apify is available in your conversations.
Does Apify work with ChatGPT and Cursor as well as Claude?
Yes. Once Apify is connected in Elaichi, the same endpoint, https://api.elaichi.ai/mcp, works in Claude, ChatGPT, Cursor, any other MCP client and the Elaichi Agent. You connect Apify once and every client picks it up.
What can an AI agent actually do with my Apify data?
With Apify connected, an agent can search the Apify Store for actors, read their details and docs, start an actor run and follow its log, and read the results from datasets and key-value stores. It can also create, update, publish or unpublish actor tasks, add schedules, and abort a run that has gone wrong. Short, concrete asks such as "show me the last five runs of the pricing scraper" work better than long instructions.
Does connecting Apify give the AI access to my whole Apify account?
An agent working through Apify only sees the actors, runs, datasets and stores that the person who signed in can already see in Apify. Elaichi can narrow that further by restricting actions for a team or role, but it never widens what Apify itself allows.
Can I stop an agent from changing things in Apify?
Yes. Restrictions in Elaichi apply per action, so you can let an agent read Apify datasets and run logs while blocking it from starting runs, aborting them, or editing and publishing tasks. A restricted action is never advertised to the AI client, so no prompt can reach it.
What happens to an Apify connection when someone leaves?
Offboarding a person in Elaichi ends their access to Apify through every client at once. If they shared an Apify connection, it keeps working for everyone else on the team. Disconnecting Apify once in Elaichi removes it from Claude, ChatGPT, Cursor and every other connected client.
Does the Apify MCP connector work with Gemini, Codex, Claude Code or other MCP clients?
Yes. Apify is reached over the same MCP endpoint every client uses, so anything that speaks MCP can call it — Gemini, Codex, Claude Code, Windsurf, Cline, Zed and OpenCode among them — alongside Claude, ChatGPT, Cursor, and the Elaichi Agent. The tools on offer and the access behind them are identical whichever client asks. Only the setup screen differs.
Is Elaichi an alternative to Zapier MCP for Apify?
Yes. Both let Claude, ChatGPT or Cursor use Apify. Zapier MCP fits a team that already automates in Zapier, since each person signs in and acts as themselves in that account. Elaichi fits when IT wants one address for the whole company, per-tool rules by role, and a record of every Apify call.
How is Elaichi different from Composio for Apify?
Composio gives AI agents tools and sign-in handling across 1,000+ apps, for developers building agents or people using an assistant, billed per tool call. Elaichi gives a company's own people governed access to Apify: one address, restrictions per role or user, and $15 per user per month. Both have role permissions and a log of every call.
Put Apify in front of your team
14 days on Gold, no credit card. Connect it once and pick what each team can call.
- Works with
-
and any other MCP client, or the Elaichi Agent.
- When the trial ends
- Nothing is deleted. Connections, roles and the audit log stay where they are, so subscribing picks up exactly where you left off.