AI agents call check_local_notifications to retrieve information from Todos without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and reports on local notification state (due-dates, SLA, stale-task, completed-run, calendar reminders) and optionally triggers local hooks and watch evaluations. It performs no creation, modification, deletion, or execution of external operations—only status inspection and optional local event emission.
From the tool's definition Tool name 'check_local_notifications' and description indicate it 'Check[s]' alerts and 'emit[s]' evaluations—purely informational operations with no data modification. Keywords: 'check', 'emit', 'alerts', 'evaluations' all denote read-only querying.
Attacks that exploit this kind of access
Check local due-date, SLA, stale-task, completed-run, and calendar reminder alerts; optionally emit local hooks and terminal watch evaluations. It is categorised as a Read tool in the Todos MCP Server, which means it retrieves data without modifying state.
Register the Todos MCP server in PolicyLayer and add a rule for check_local_notifications: 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 Todos. Nothing to install.
check_local_notifications is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the check_local_notifications 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 check_local_notifications. 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.
check_local_notifications is provided by the Todos MCP server (@hasna/todos). 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 →