AI agents use set_primary_machine to create or update resources in Mementos — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mementos environment.
This tool modifies configuration state (machine primary status) but does not irreversibly delete data. The operation is reversible—another machine can be marked primary, restoring the prior state. The severity is medium because misuse could disrupt agent coordination or system behavior if the wrong machine is selected, but no data is lost.
From the tool's definition Tool description states 'Mark a machine as the primary machine' — a state-modification operation. The constraint 'Only one primary machine is allowed at a time' indicates this overwrites prior state, making it a reversible Write rather than Destructive.
Attacks that exploit this kind of access
Mark a machine as the primary machine. Only one primary machine is allowed at a time. It is categorised as a Write tool in the Mementos MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mementos MCP server in PolicyLayer and add a rule for set_primary_machine: 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 Mementos. Nothing to install.
set_primary_machine 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 set_primary_machine 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 set_primary_machine. 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.
set_primary_machine is provided by the Mementos MCP server (@hasna/mementos). 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 →