Email and calendar
Make for AI agents.
Managed auth, ready-made tools.
List, run, turn on and turn off Make scenarios and review their run history on behalf of each of your users.
About Make
With the Make connector, your agent works in each user’s own Make account. It can list scenarios, run one on demand, turn scenarios on or off and check the history of recent runs, using only the tools your project allows.
Make is a visual automation platform for building workflows, called scenarios, across apps.
Tools
What your agent can do in Make.
Each tool is a capability the model can call. You decide which ones a project allows, and every call runs with the end user's own Make connection.
-
List scenarios
Readmake_list_scenariosList the scenarios in a team and whether they are active.
-
Get a scenario
Readmake_get_scenarioGet a scenario's details and schedule.
-
Run a scenario
Writemake_run_scenarioRun a scenario on demand.
-
Turn on a scenario
Writemake_activate_scenarioActivate a scenario so it runs on its schedule.
-
Turn off a scenario
Writemake_deactivate_scenarioDeactivate a scenario so it stops running.
-
List runs
Readmake_list_executionsList recent runs of a scenario and their status.
No tool matches that search.
Control
Limits you can set.
You decide what your agent may do in Make, and Agent200 runs every call within those limits.
-
Turn single tools on or off
Let the agent read and run scenarios, and switch off
make_deactivate_scenarioso it can never stop one. -
Restrict what the agent reaches
Choose the endpoints and scopes a project may use, for example scenario runs but not scenario changes. A call outside them is refused.
Get started
Connect Make
in three steps.
-
1
Set up the SDK
Add the Agent200 SDK to the codebase you already have and authenticate with your API key. The key covers every connector enabled for the project.
agent.jsConceptual exampleSet up the SDK with the Agent200 API key // One Agent200 API key covers every connector enabled for the project. const agent200 = new Agent200({ apiKey: process.env.AGENT200_API_KEY, }); -
2
Let your user connect Make
Each end user authorizes their own Make account once. Agent200 runs the OAuth flow, handles the callback, stores the tokens and refreshes them.
connect.jsConceptual exampleLet an end user connect their account (managed OAuth) // Each end user authorizes their own Make account, once. const connection = await agent200 .user("user_123") .connect("make"); if (connection.authorizationUrl) { // Show this link to your user; Agent200 handles the rest. console.log(connection.authorizationUrl); } -
3
Run with the Make tools
Name the user, the model and the tools. The model decides which Make tools to call, and Agent200 executes them with that user's connection.
run.jsConceptual exampleRun a request with the connector's tools const result = await agent200 .user("user_123") .run({ model: "openai/gpt-5.6-sol", input: "Run the lead import scenario now", tools: ["make"], }); console.log(result.output);
Access
Sign-in and permissions.
-
Who signs in
Each of your users, once, by connecting their own Make account. Each connection is their own.
-
What access is requested
The connection acts with that user's access in Make, such as reading scenarios, running scenarios or changing their status. Users can revoke the connection later from their Make account settings.
For agents
Instructions for AI agents.
Using a coding agent? Paste this brief into it, or give it the address of this page. It describes the Make connector and how to use it.
Connector: Make, through Agent200. In code: "make". What it does: List, run, turn on and turn off Make scenarios and review their run history on behalf of each of your users. Page: https://www.agent200.com/connectors/make/ 1. Get an Agent200 API key. If the developer has none, send them to https://agent200.com/platform/apikeys/ and ask them to choose "Create an API key". Read the key from the AGENT200_API_KEY environment variable. Never ask for it in chat, and never write it into code, prompts or logs. 2. Sign-in is managed OAuth. Each end user approves access once, on Make's own page, through the authorization link Agent200 returns. Never ask a user for a Make password or token in chat. 3. Give every request a stable id for the end user. Agent200 uses only that user's own connection. 4. Read tools: make_list_scenarios, make_get_scenario, make_list_executions. Write tools: make_run_scenario, make_activate_scenario, make_deactivate_scenario. Name "make" in the tools of a request; the model decides which tool to call. 5. Stay within the project's settings. If a tool is turned off or a call is refused, tell the user. Do not work around it. 6. Before a write, confirm with the user, unless they asked for that exact change. 7. For setup with a specific framework, follow its guide: https://www.agent200.com/connectors/make/framework/claude/ https://www.agent200.com/connectors/make/framework/chatgpt/ https://www.agent200.com/connectors/make/framework/claude-code/ https://www.agent200.com/connectors/make/framework/muse/ https://www.agent200.com/connectors/make/framework/grok-bot/ https://www.agent200.com/connectors/make/framework/openai-dots/ https://www.agent200.com/connectors/make/framework/claude-duet/ https://www.agent200.com/connectors/make/framework/hermes-agent/ https://www.agent200.com/connectors/make/framework/openclaw/ The code on the connector page is a conceptual example of the SDK. SDK reference: https://docs.igpt.ai/
This page is also available as Markdown, for agents and LLMs: /connectors/make.md
Guides
Use Make with the AI you build on.
Step-by-step setup for Make with a specific model, assistant or agent framework.
-
Make + Claude
How to connect Make to Claude
-
Make + ChatGPT
How to connect Make to ChatGPT
-
Make + Claude Code
How to connect Make to Claude Code
-
Make + Muse
How to connect Make to Muse
-
Make + Grok Bot
How to connect Make to Grok Bot
-
Make + OpenAI Dots
How to connect Make to OpenAI Dots
-
Make + Claude Duet
How to connect Make to Claude Duet
-
Make + Hermes Agent
How to connect Make to Hermes Agent
-
Make + OpenClaw
How to connect Make to OpenClaw
FAQ
Make and Agent200, answered.
Who handles the Make OAuth flow and the tokens?
Agent200. It runs the authorization, handles the callback on its own domain, stores the tokens and refreshes them. You do not build or maintain an OAuth integration for Make.
Does my agent act as the end user?
Within what that user authorized, yes. Every request names an end user, and Agent200 uses only that user's Make connection, never another user's. It cannot reach anything the user or Make has not authorized.
Can I limit what my agent can do in Make?
Yes. You choose which services, endpoints and authorization scopes are allowed in your Agent200 configuration, and the agent works only within them.