Every tool call on the laptop
Shell commands, cloud CLI calls, scripts, file writes and MCP tools. Checked before they run.
Endpoint Guard runs on Windows and Mac laptops. It finds the AI tools your people use, shows what they use them for, and checks every action an AI assistant takes on the laptop.

Shell commands, cloud CLI calls, scripts, file writes and MCP tools. Checked before they run.
Write the rule the way you would say it: "Never delete anything in production AWS."
Apps, coding assistants and local models. Work use and personal use.
Jamf, Rippling or Microsoft Intune. Windows and macOS.
Most AI security tools check MCP tool calls. AI assistants also run shell commands, call cloud CLIs and write scripts, using the employee's own credentials. Endpoint Guard checks all of them.
| What gets checked | MCP-only tools | Cortega |
|---|---|---|
| MCP tool calls | ✓ | ✓ |
| Shell commands | – | ✓ |
| Cloud CLI calls, such as AWS | – | ✓ |
| Scripts and SDK code the assistant writes | – | ✓ |
| Access to credential files | – | ✓ |
| Your own rules, in plain English | – | ✓ |
"Never change anything in our production AWS account. Reading is fine."
"Never download a script and run it."
"Keep AI assistants away from cloud credential files."
"Ask the developer before a staging deploy."
aws ec2 terminate-instances --profile prodBlockedaws s3 ls --profile prodAllowedcurl https://… | shBlockedcat ~/.aws/credentialsBlockedaws lambda update-function-code --profile stagingAsks firstA blocked command does not run. The assistant is told why and does not try another way. An approver can allow it for an hour. Works with Claude Code, Codex and Cursor.
ChatGPT, Claude, Copilot, Gemini, Cursor and more. Local models such as Ollama, too.
See which AI use is for work and which is not.
Tokens, cost and lines of code for each person, even on their own subscriptions.
Read prompts when your policy allows. List the code repositories on each laptop. The scan never uploads code.
Choose watch, protect or block for each AI app.
Personal data, health data and keys are masked or blocked before they leave.
Checks run on the laptop. They keep working when Cortega cannot be reached.
App policy
Choose how Endpoint Guard treats traffic from an app, independently of model routing.

Local guardrails
The guardrail editor exposes request and response checks, user notifications and local detection options.

AI assistants
The AI Assistants screen has distinct controls for gateway routing, usage collection, message content and repository inventory.

Device enrollment
Use certificate enrollment or an SSO invitation. The form records the target Cortega URL, device identity and certificate lifetime.

Push Endpoint Guard and a device certificate from your MDM. Each laptop enrolls itself.
Read the deployment guide →Send approved assistants through AI Border Gateway for model choice and team budgets.
See coding assistant governance →An agent on each laptop applies your app policies and checks. Results go to the Cortega console.
Observe and police modes inspect configured app domains. Police mode adds local guardrails; each guardrail can log, mask, or reject content on requests, responses, or both. Domains outside inspection scope remain encrypted.
Set recording and data-handling policies for endpoint observability. AI Verifier and Cortega Agents are enabled separately for selected traffic; they are not part of the local guardrail execution path.
Shadow AI
Start with a few laptops. Add your MDM when you are ready.