AI agents use logout-all to create or update resources in Moxis — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Moxis environment.
Logging out from all registered instances is a reversible write/state-change operation — it terminates active sessions across all instances, but sessions can be re-established via login. It is not destructive (no data deleted), not financial, and not merely a read. The blast radius is medium since misuse would disrupt access to all registered MOXIS instances simultaneously, requiring re-authentication.
From the tool's definition logout from all registered MOXIS instance
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
logout from all registered MOXIS instance. It is categorised as a Write tool in the Moxis MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Moxis MCP server in PolicyLayer and add a rule for logout-all: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Moxis. Nothing to install.
logout-all is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the logout-all rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for logout-all. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
logout-all is provided by the Moxis MCP server (@xitrust-pub/moxis-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →