AI agents use notify_session_progress to create or update resources in AFK Mode — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your AFK Mode environment.
The tool writes/sends data (a progress notification) to a connected mobile client. It has no destructive, financial, or code-execution effects. It is not a pure read since it actively pushes data outward. Severity is low because misuse would at worst send spurious notifications to a mobile device.
From the tool's definition 'Sends a progress update to the connected mobile client' — pushes a notification/message to an external client
Attacks that exploit this kind of access
Sends a progress update to the connected mobile client. Only call this when AFK mode is active (afkMode: true and clientConnected: true). Returns immediately. Use category. It is categorised as a Write tool in the AFK Mode MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the AFK Mode MCP server in PolicyLayer and add a rule for notify_session_progress: 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 AFK Mode. Nothing to install.
notify_session_progress 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 notify_session_progress 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 notify_session_progress. 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.
notify_session_progress is provided by the AFK Mode MCP server (paulbennet/afk-mode-mcp). 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 →