AI agents use set_focus 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.
set_focus modifies an agent's active context or configuration setting (which project is in focus), which qualifies as Write since it creates or modifies data reversibly without deleting or executing external commands. The modification is reversible by setting a different focus.
From the tool's definition Tool description states it "Set focus for an agent on a project" and modifies which project "Memory ops will auto-scope to" — this changes agent state/configuration reversibly.
Attacks that exploit this kind of access
Set focus for an agent on a project. Memory ops will auto-scope to that project. 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_focus: 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_focus 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_focus 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_focus. 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_focus 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 →