Make for AI agents
Make is a visual automation platform that connects apps and services into workflows called scenarios, without requiring a team to write code. Connect it once through Arc0, and your agent, or Claude, ChatGPT and Cursor, can use it through one MCP endpoint, limited to what each user approved.
What agents do in Make.
Check a scenario's run logs
Pull recent execution logs for a scenario to debug why a run failed, read-only.
Look up a connection's status
Check whether a connection used by a scenario is still active before troubleshooting.
Approve before deleting a scenario
Require approval before deleting a scenario, since it stops every automation built on it.
39 Make actions, graded by risk.
Every Make action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
35Look things up. Allowed by default.
- make.get_hookGet Hook
- make.get_teamGet Team
- make.list_teamsList Teams
- make.get_hook_logGet Hook Log
- make.get_users_meGet Current User
- make.get_connectionGet Connection
- make.get_operationsGet Operations
- make.list_scenariosList Scenarios
- make.get_organizationGet Organization
- make.list_connectionsList Connections
- make.get_scenario_logsGet Scenario Logs
- make.get_cashier_pricesGet Cashier Prices
- make.list_enums_localesList Enums Locales
- make.list_organizationsList Organizations
- make.get_enums_imt_zonesGet Enums IMT Zones
- make.get_cashier_productsGet Cashier Products
write
2Create and change things. Allow, or ask the user first.
- make.update_scenarioUpdate Scenario
- make.create_organizationsCreate Organization
destructive
2Delete, cancel or archive. Ask first, or deny outright.
- make.delete_scenarioDelete Scenario
- make.create_users_password_reset_demandCreate Password Reset Demand
Make in three steps.
- 01Your users connect MakeThey add their Make api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, writes like “create Organization” can wait for the user, and “delete Scenario” can be denied outright.
- 03Any agent can actYour agent calls Make through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('make', { read: 'allow', write: 'ask', // create_organizations destructive: 'deny', // delete_scenario }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Make connects.
Users add their Make api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.
The same Make connection serves your agent over MCP and your own backend over REST and the proxy, so a user connects once. How Arc0 handles credentials →
- AUTH
- API key
- CREDENTIALS
- Per-tenant encrypted vault
- MODEL SEES
- Results only, never credentials
- AUDIT LOG
- Every call, on every plan
Use Make from any agent.
Make and Arc0, answered.
Can I use Make with Claude, ChatGPT or Cursor?
Yes. Connect Make to Arc0 once, then add your Arc0 MCP URL to Claude, ChatGPT, Cursor, Claude Code or any other remote-MCP client. Each assistant only gets the Make actions you allow.
How do users connect Make?
Users add their Make api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.
Which Make actions can my agent take?
39 in total: 35 read, 2 write and 2 destructive, such as “create Organization”. Your policies decide which of them each agent may call.
Can I stop my agent from deleting things in Make?
Yes. Actions like “delete Scenario” are graded destructive. Set destructive actions to deny, or to ask so the user approves each one, and blocked calls still show up on the audit log.
Can my own backend call Make too?
Yes. The same Make connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Make into your agent.
Your users connect Make once, under your brand. Your agent gets 39 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan