Control what the agent can do: tools & permissions
More AI’s agent can read and write files, run commands, search the web, schedule routines and connect to your other apps. Every capability is yours to switch off, and risky actions ask before they run.
The More AI team · Updated June 14, 2026
One switchboard for every capability
Settings → Agent tools lists every built-in capability with its own switch. Turn one off and it is removed from the agent’s toolset entirely, in every mode — Chat, Cowork, Code and headless routines. This is policy, not a per-message prompt: a disabled tool simply never reaches the model.
The permission model
Beyond the on/off switches, sensitive actions are gated as they happen. Deleting a file always asks first. In Code mode, access modes decide how much the agent may do on its own — read-only approves everything, while a freer mode still pauses for risky commands. Every approval can be granted just once, for the session, or always.
Connect your own apps
Connectors (via MCP) let the agent reach tools like Gmail, Google Drive or your own services. Each connector’s read actions can run freely while writes ask for confirmation, and you choose exactly which connectors any routine is allowed to use.
Safe by default for unattended runs
Because a scheduled routine runs with no one watching, it gets read-only tools only — destructive, gated actions are withheld. You stay in control of what your automation can ever touch.
Frequently asked questions
What happens when I turn a tool off?
It is removed from the agent’s toolset entirely, in every mode — Chat, Cowork, Code and routines. A disabled tool never reaches the model; it is policy, not a per-message prompt.
How are risky actions handled?
Sensitive actions are gated as they happen — deleting a file always asks first — and every approval can be granted just once, for the session, or always.
Can the agent connect to my other apps?
Yes, through connectors (via MCP) such as Gmail or Google Drive. Read actions can run freely while writes ask for confirmation, and you choose which connectors each routine may use.
Can I stop the agent from running commands or using the web?
Yes. Settings → Agent tools has a switch for every capability; turn one off and it is removed from the agent’s toolset entirely, in every mode. A disabled tool never reaches the model — it is policy, not a per-message prompt.
Do these controls apply to scheduled routines too?
Yes — and routines are stricter: because no one is watching an unattended run, they get read-only tools, with destructive and gated actions withheld regardless of your other settings.