Every AI on every device
Copilot, ChatGPT, Claude Code, Cursor and agents nobody registered, found on Windows and macOS.
- AI tools and agents inventoried
- Local MCP servers found
- Deployed with Intune, Jamf or Kandji
Copilot, ChatGPT, Claude Code and Cursor work with source code, credentials and production access on staff devices. Zenstra AI Discovery sees the prompt, the tool call and the device together.
A coding agent can read secrets, run shell commands and push changes. Hijacked, it does all that with the developer’s own access.
claude-codeThe agent helps a developer debug a service on their laptop.~/.awsIt tries to read cloud credentials it was never asked to touch.Zenstra AI DiscoveryThe prompt, the tool call and the device are seen together, on the device.claude-code · read ~/.awsRolled out with Intune, Jamf or Kandji. Stop one agent on one device without isolating the laptop.
denysecrets.read~/.aws, ~/.ssh · unless in taskholdshell.execin prod · step-up requireddenymcp.serverwhen unregistered on deviceallowrepo.readwithin the open workspaceZenstra AI Discovery runs on Windows and macOS and is deployed through your device management.
Copilot, ChatGPT, Claude Code, Cursor and agents nobody registered, found on Windows and macOS.
Prompt-to-action lineage connects what the agent read to what it tried to do, so a helpful agent is not treated like a hijacked one.
Stop the agent and keep the laptop working. The developer carries on while the agent is contained.
Injected instructions in a repo or issue.
Agents reading ~/.aws, tokens and env files.
Staff sharing keys and data with chat tools.
Unreviewed tools added to local agents.
Shell and deploy actions held for step-up.
Unregistered agents on staff devices.
Routine work is allowed inline. Only actions outside policy are held or blocked, with a clear reason.
Windows and macOS, deployed with Intune, Jamf or Kandji.
No. It complements it by understanding the AI agents on the device.