The server itself exposes 24 tools, and some of them can write to your Make account. Behind TrustGate an agent only sees the tools you allow, requests and responses are inspected, and every call is logged. Anything outside the allowlist is denied before it reaches Make.

How is this different from connecting Make MCP directly?

Connected directly, an agent sees every tool the server exposes and holds the credential itself. Through TrustGate you choose which tools each agent gets, and every call is logged against the agent that made it.

What if the Make MCP API changes?

We track the Make MCP schema, so the tool catalogue stays current. Tools you have already allowed keep working, and anything new stays denied until you enable it.

Can I give different agents different Make tools?

Yes. Access is set per agent: one can get a handful of read tools, another the full set. You grant the whole MCP or single tools within it.

Where can I see what my agents did in Make?

Every call is logged against the agent that made it, with the tool it used. Activity can be sent on to your own monitoring.

Do I need to run the Make MCP server myself?

No. TrustGate connects to the Make MCP server and sits in front of it. Your agent only talks to your TrustGate URL, never to Make directly.

Connect Make MCP to your AI agents, securely.

One secured endpoint for every Make call your AI agents make, scoped per user, inspected, and logged.

Get started for free

Get a demo

Try Make MCP now

What your agents can ask once Make MCP is connected.

Select the tools your AI agents can call

24 tools from the Make MCP schema.

Showing 24 tools

scenarios_runhigh riskExecute a scenario with optional input data.
scenarios_interfacereadGet the interface for a scenario.
scenarios_listreadList all scenarios for a team. Results can be narrowed to one folder (optionally including its subfolders) and/or to scenarios carrying at least one of the given scenario labels.
scenarios_getreadGet a scenario and its blueprint by ID.
scenarios_createwriteCreate a new scenario from a blueprint. Verify every module name in the blueprint via app-modules_list before creating — never invent module identifiers.
scenarios_updatehigh riskUpdate a scenario.
scenarios_deletehigh riskDelete a scenario.
scenarios_activatehigh riskActivate a scenario. Required before scenarios_run can execute it.
scenarios_deactivatehigh riskDeactivate a scenario. If this fails with 'Scenario is not running', the scenario is already inactive — treat that as success and do not retry.
scenarios_set_interfacewriteUpdate the interface for a scenario.
data-stores_listreadList all data stores for a team.
data-stores_getreadGet data store details by ID.
data-stores_createwriteCreate a new data store.
data-stores_updatehigh riskUpdate a data store.
data-stores_deletehigh riskDelete a data store.
data-store-records_listreadList all records in a data store.
data-store-records_createwriteCreate a new record in a data store.
data-store-records_updatehigh riskUpdate an existing record in a data store.
data-store-records_replacehigh riskReplace an existing record in a data store or create if it doesn't exist.
data-store-records_deletehigh riskDelete specific records from a data store by keys.
connections_listreadList connections for a team.
connections_getreadGet details of a specific connection.
teams_listreadList the teams of an organization. Requires an organizationId — get it from organizations_list, whose response also includes each organization's teams (id and name).
teams_getreadGet details of a specific team.

What Make MCP exposes

Make MCP groups its 24 tools into 4 categories, each with a suggested starting policy.

All 24 tools as JSON, ready to paste.

Category	Covers	Access	Suggested policy
Scenario Runs	Running active scenarios with input data, and reading a scenario's input and output interface	Read / Write	Require approval before running; a scenario can reach any connected service
Scenarios	Listing, details, creation, updates, activation, deactivation, deletion and interface setup	Read / Write	Approve updates, activation and deletion
Data Stores	Data stores and the records inside them: listing, creation, updates, replacement and deletion	Read / Write	Audit record changes; scenarios read from these
Connections & Teams	Connections and teams	Read	Connections hold credentials to other services; restrict tightly

Connect Make MCP to your AI agent

Four steps, under ten minutes.

01
Sign in to NeuralTrust
Open the NeuralTrust platform, sign in and go to Getting started, then Connect your tools.
02
Choose your agent
When asked which agent you use, pick Claude Code, Codex, Cursor, Windsurf, Copilot or your own code.
03
Connect Make
Find Make in the tool list and connect it.
04
Connect your agent
Follow the steps on screen to add the config to your agent, then send the test prompt.

Permissions down to the single tool

You do not allow Make MCP or block it. You allow the exact tools each agent can call, one by one.

Make MCP	24 TOOLS AVAILABLE
Code review agent	4 tools, read only
Issue triage bot	9 tools
Platform team assistant	all 24 tools

Tool by toolConnecting the server is not the unit of access. Each tool is granted on its own.
Default denyA tool you have not enabled is never exposed to the agent.
Approval on writesTools that change or delete things can require a human to confirm.

Is Make MCP secure?

One endpoint instead of raw credentials. Every call is checked against policy and logged.

AI agentsConnect through your MCP client configuration.	NeuralTrustApply controls based on your configuration.	Make MCP24 documented tools.
Coding assistants	Connection & credentialsper user	Data Stores10 tools
Internal copilots	Tool access policiesdeny by default	Scenarios8 tools
Workflow automations	Request & response inspectioninline	Connections & Teams4 tools
Compatible MCP clients	Activity monitoringalerts and logs	All other tools2 tools