Make
The Make connector makes your Make scenarios callable in the anymize chat so existing automations start with one sentence.
3 Min
What you can do with it
What you built in Make becomes addressable in chat. Instead of finding and starting the scenario in Make, you just say it. What is possible depends on which scenarios you enabled for access in Make.
- “Start the scenario for month-end closing.”
- “Which scenarios are available to me?”
- “Run the scenario with these values and tell me what came out.”
How to create the Make access token
- 01In Make click your name at the top right and open Profile.
- 02Open the API access tab.
- 03Under Tokens click Add token.
- 04Give a label and choose the scopes, including mcp:use as required, so scenarios show as tools.
- 05Save, copy the token and note the zone, for example eu1.make.com. After that the token is only shown shortened.
Make explains MCP tokens at https://developers.make.com/mcp-server/connect-using-mcp-token . General token creation: https://developers.make.com/api-documentation/authentication/create-authentication-token
How to connect Make
- 01In anymize open Apps, then Connectors, and search for Make.
- 02Choose the zone and paste the token from the section above. With “Test connection” you see at once how many tools are found.
- 03Connect. anymize stores the token encrypted and only sends it as a header.
After connecting, anymize offers you the official Make skills. They are worth it: they explain to the assistant how scenarios and modules in Make are built.
Does the AI start my scenarios on its own?
No. The assistant only starts what you ask it to. Because a scenario run has real effect, so it sends mail, creates records or moves files, the tile says “read and write”, not “read only”.
Make runs with direct access, so without the in-between privacy agent. The main model sees the real answers of your scenarios. That is also stated in the Connect dialog. So only enable the scenarios that belong there.
What is anonymized
What you write yourself in chat goes through anonymization: customer names, addresses, invoice numbers and account data in your request are replaced by placeholders before the query goes to an AI model.