unfocus

Remove focus for an agent (clears project scoping).

Server Mementos @hasna/mementos
Category Write
Risk class Medium
Parameters 00 required

What unfocus does on Mementos

AI agents use unfocus 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.

Why unfocus needs a policy

The tool modifies the agent's state by clearing its project scoping/focus. This is a reversible configuration change (focus can be re-set), making it a Write operation. Misuse could disrupt an agent's context awareness, but the effect is not irreversible, hence medium severity.

From the tool's definition Remove focus for an agent (clears project scoping)

Questions about unfocus

What does the unfocus tool do? +

Remove focus for an agent (clears project scoping). 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.

How do I enforce a policy on unfocus? +

Register the Mementos MCP server in PolicyLayer and add a rule for unfocus: 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.

What risk level is unfocus? +

unfocus is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit unfocus? +

Yes. Add a rate_limit block to the unfocus 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.

How do I block unfocus completely? +

Set action: deny in the PolicyLayer policy for unfocus. 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.

What MCP server provides unfocus? +

unfocus 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.

// LOOK UP ANOTHER 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 →

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.