How it worksSecurity and approval

Updated 27 Oct 2026View as Markdown

Security and approval

The rules Mindset enforces for every agent with no setup, how write operations are approved, how credentials are kept and where your data goes.

MCP serverSDK and APIYour own cloud:AWSGCPAzureor hosted by MindsetMindset platformAgentScriptSkillFunctionWidgetConnectionOperationVersionRunSecurity and complianceone posture · audit trail · personal data redactionBuilderscoding agentOperatorsAI clientor the StudioYour appthe SDKYour serverthe APIThe Huband schedulesBuilderscoding agentOperatorsAI client or the StudioMCP serverYour own cloud:AWSGCPAzureor hosted by MindsetMindset platformAgentScriptSkillFunctionWidgetConnectionOperationVersionRunSecurity and complianceone posture for the org,audit trail and personal data redactionSDK and APIYour appthe SDKYour serverthe APIThe Huband schedules

Every agent runs under these rules, with nobody setting them up. With the settings your admins choose, they make up your org's compliance posture. If you write your own agent policy, list them as controls the platform enforces.

Why it matters#

No agent ships without these controls, and no agent can grant itself a write. A person, or a setting only an admin controls, decides which writes exist.

What Mindset enforces#

RuleWhat holds
Operations are the only way outAn agent, script or function reaches an outside system only through an operation on a connection. There's no general web or HTTP tool, so even a hijacked agent can reach only its operations
Writes need consentOnce per operation, from a person or the org setting. No agent can give it
Untested writes don't go liveBehavior tests refuse every write, and test runs write only what an admin agreed to. A script or function that calls an operation with no successful call since its last lapse can't go live unless an admin overrides it on the record. See the go-live gate
Every action is recordedMindset records each model call and operation call in the run's record, and each change in the audit record, so an agent can't skip either. The database refuses deletes from the audit record. See Runs and Audit and personal data
Environments can't see each otherAn agent in Sandbox can't reach a connection in Production, and an API key works only in the environment it was issued into. See Environments

Approving writes#

A write operation needs consent before anything can call it. It's given once per operation, never per call, and after that the write runs whenever an agent calls it. A read never needs consent.

ConsentMeaningCan an agent call it?
Not requiredA readYes, once it's enabled, available and assigned
PendingA write waiting for a person to enable it. The Studio shows Enable itNo. A call is refused, not queued
GrantedA person, or the org setting, agreed to itYes

A person's consent is recorded with their name and the time. A write whose definition changes needs consent again.

Your org's default: On (auto-enable)

One org setting decides what happens to a new write: Enable actions that change other systems automatically, under Settings → Systems. Only an org admin can change it.

SettingA new write operation
On (auto-enable), the defaultIs granted as soon as it's registered, so your AI client can enable it with no person involved
OffWaits as Pending until a person enables it on the connection

Locking and disabling

ButtonOnWhat it does
Lock operationAny operationStops every caller. Only a person can enable it again
Enabled switchA whole connectionTurned off, refuses every call to any of its operations before anything leaves

Each takes effect on the next call, with no new agent version.

No agent can enable a write that's waiting for a person, or enable again an operation a person locked, and the server refuses both from anything but a signed-in person, including an API key. An agent that registers such a write gets a link to the connection's page to pass to an admin.

Consent can't say yes to one supplier query and no to another. For that, a script asks a person before the action and parks the run until they answer.

Live demoHelp widget · LedgerlyA billing help agent reads charges over MCP and stops at a refund nobody has approved.

Credentials never reach the agent or the model#

A connection's credential is kept in a secret store and never put into an agent's context or sent to a model. A person enters it on a separate Enter a secret value form, and the model gets back only the field's name. A call aimed at a different host than the connection's is refused before the credential is looked up.

The outside system sees the connection's account, shared or the person's own, so it can't tell which agent called. Mindset's audit names the agent. Scope each credential to what its operations need.

Where your data goes#

DataWhere it goes
Your org's agents, conversations, runs and auditThe Mindset deployment your org lives on. Its region is fixed when the org is created
Model calls by your agentsThe provider whose model key your org set: Anthropic, OpenAI or AWS Bedrock
Model calls by Orca and the buildersPlatform-provided keys, unless an admin turns on Run the built-in agents on our own key
Model calls with AWS BedrockYour AWS account, in the region you name. Some models route across that region's geography, which can include other countries
Knowledge search embeddingsOpenAI text-embedding-3-large, on your own embedding key and endpoint if you set them, otherwise the deployment's
Outside systemsOnly what an operation sends, to the connection's own host

Personal data can be replaced with placeholders before it reaches the model provider (off by default). See Audit and personal data.

What Mindset doesn't enforce#

  • Behavior tests before go-live. Saving and activating don't run them. See Test behavior.
  • Cost caps or data residency on an AI model connection. Its limits are the size cap and personal data protection.
  • Ownership and housekeeping. Owners, backups and archiving unused agents are your team's conventions. See Roll out Mindset.

Every org setting, with its default, is on Org settings. To approve or withdraw a write, see Approve what agents can do.