Make MCP connector
The Make connector brings your Make scenarios into Claude, ChatGPT, Cursor and the Elaichi Agent, so your team can run, check and manage automations by asking, inside their own Make access, with every action 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 Make to Claude, ChatGPT or Cursor
Two steps, about a minute.
In Elaichi
Connect Make once
-
Open Connections, choose Add connection, and pick Make.
-
Optionally set Share with to give a team access, then press Connect.
-
Approve it in Make. Make'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.
Make 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.
Make 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.
Make 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 Make 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 Make through Elaichi
Every one of these runs inside the access the person already has, and lands in the same audit log.
-
Operations
Run a scenario the moment it is needed
Ask for the order sync scenario to run right now instead of waiting for its next schedule, then get told whether it finished cleanly.
-
Marketing
Check which campaign automations ran overnight
Ask which Make scenarios ran since yesterday and which ones stopped with an error, so a broken lead handoff is caught before the morning standup.
-
Sales
Pause a CRM sync during a data cleanup
Switch off the scenario that writes to the CRM while the team tidies records, and switch it back on when they are done.
-
Support
Find the scenario that routes tickets
Ask which Make scenario handles ticket routing, what it is connected to and when it last ran, without digging through the Make dashboard.
-
IT
Review every active scenario in one place
List the scenarios running in each Make team, see who owns them and spot the ones nobody has touched in months.
-
Finance
Confirm the invoice automation finished
Ask whether the end-of-month invoice scenario completed and how many runs it made, then ask for it to run again if a batch was missed.
Try asking
- “Run the lead sync scenario now and tell me how it went.”
- “Which Make scenarios failed in the last 24 hours?”
- “Turn off the Slack digest scenario until Monday.”
Compare
Elaichi vs Zapier MCP vs Composio for Make
All three can connect Make 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 Make tools | Allow or restrict single Make 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 Make 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.
See it in Elaichi
What connecting Make gets you
5 screens from the product, each doing one job for your Make account.
The agent
Ask Make which scenarios ran overnight.
Plain questions, answered from live Make scenarios and their run history.
- scenarios
- runs
- webhooks
- data stores
Ask Elaichi to work across your apps.
Run the lead sync scenario now and tell me how it went.
Which Make scenarios failed in the last 24 hours?
Turn off the Slack digest scenario until Monday.
Also runs in Claude, ChatGPT or Cursor
MCP clients
One endpoint puts Make in every client.
Claude, ChatGPT and Cursor reach Make through one governed endpoint, no SDK, no shared API key.
ElaichiMCP clientsClaude
ChatGPT
Cursor
Copy the endpoint
Toolboxes
Each team gets its own Make toolbox.
Operations runs scenarios, Marketing checks its own, nobody sees the other team's automations.
- Operations
- Marketing
- Sales
- Support
ElaichiToolboxesShared connections
Share Make without sharing a login.
Teammates run scenarios through one Make connection and never see the credential behind it.
- Operations
- Marketing
- Sales EMEA
- Support
ElaichiConnectionsAudit log
Every Make run names who started it.
When, who, what happened and which scenario, kept in an append-only log.
- When
- Who
- What happened
- Type
ElaichiAudit logLaunching 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 Make work itself.
Runs are fetched, grouped and drafted into a digest, approved by a person, posted back.
Make digest
Run 418 · started 2 minutes ago · on behalf of Emily Carter
-
✓
Schedule
Every weekday at 8:00 AM
0.2s -
✓
Fetch scenarios
Make
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
Make
Queued
Collections and dashboards
Make scenario health, computed without a model.
Four metrics, 14 days of runs and a team breakdown, refreshed on schedule.
Make health
Refreshed 4 minutes ago · every 15 minutes · from the scenarios collection
Scenarios
1,284 ↓ 12%
Runs
96 ↓ 8%
Needs attention
3 ↑ 2
Updated this week
412 ↑ 9%
Scenarios created
Last 14 days
By team
Share of activity
Operations 34%
Marketing 27%
Sales EMEA 21%
Support 18%
Related connectors
More from the catalog
FAQ
Frequently asked questions
How do I connect Make to Claude?
Open Elaichi, choose Make and sign in to your Make account over OAuth, the same way you would sign in to Make itself. There is no OAuth application to register and no client ID or secret to generate. Then in Claude go to Customize, then Connectors, then Add, and paste https://api.elaichi.ai/mcp as the endpoint. Claude asks you to sign in to Elaichi and Make is ready to use.
Does Make work with ChatGPT and Cursor as well as Claude?
Yes. Once Make 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 Make once and every client picks it up.
What can an AI agent actually do with my Make account?
With Make connected, an agent can run your scenarios on request, check which ones ran or failed, and turn scenarios on or off. What is available follows what your Make account has set up, and managing scenarios needs a paid Make plan. Short, concrete asks such as run the lead sync scenario now tend to work better than long paragraphs.
Does connecting Make give the AI access to every scenario and team?
No. Access to Make follows the person who signed in, so the agent only sees the Make teams and scenarios that person can already open. Elaichi can narrow that further with restrictions, and it can never widen it beyond what Make itself allows.
Can I stop an agent from changing or deleting scenarios in Make?
Yes. Restrictions in Elaichi apply per action, so you can let people run and check Make scenarios while blocking changes to them. A restricted action is never shown to Claude, ChatGPT or any other client, so no prompt can reach it.
What happens to a Make connection when someone leaves?
Offboarding that person in Elaichi ends their access to Make at once, across every client they used. A shared Make connection keeps working for everyone else on the team. If you disconnect Make in Elaichi, it is removed from every client in one step.
Does the Make MCP connector work with Gemini, Codex, Claude Code or other MCP clients?
Yes. Make 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 Make?
Yes. Both let Claude, ChatGPT or Cursor use Make. 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 Make call.
How is Elaichi different from Composio for Make?
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 Make: one address, restrictions per role or user, and $15 per user per month. Both have role permissions and a log of every call.
Put Make 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.