AI agents use disable_afk_mode to create or update resources in Memex — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Memex environment.
This tool changes the AFK (Away From Keyboard) mode setting, which is a reversible state modification. It is Write category because it updates configuration state. Severity is low because toggling AFK mode has minimal blast radius—it affects only the mode flag, not critical data or operations. The effect is easily reversible via enable_afk_mode.
From the tool's definition Tool modifies state ('Turn off AFK mode') and returns confirmation of state change ('disabled': True). No irreversible data deletion, external code execution, or financial impact.
Attacks that exploit this kind of access
Turn off AFK mode. Returns {"disabled": True} when AFK was. It is categorised as a Write tool in the Memex MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Memex MCP server in PolicyLayer and add a rule for disable_afk_mode: 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 Memex. Nothing to install.
disable_afk_mode 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 disable_afk_mode 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 disable_afk_mode. 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.
disable_afk_mode is provided by the Memex MCP server (queflyhq/memex). 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 →