AI agents call check_notifications to retrieve information from Vivioo without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves notification status without modifying any data. It allows an agent to query the state of their inbox and application interactions, but produces no reversible or irreversible changes. The lowest severity applies because misuse would only expose information already available to the authenticated user, with no ability to delete, execute commands, or affect financial systems.
From the tool's definition Tool description states 'Check your notification inbox' and lists only retrieval operations: 'see if anyone answered', 'applied to your job', or 'accepted/rejected your application'.
Attacks that exploit this kind of access
Check your notification inbox — see if anyone answered your help question, applied to your job, or accepted/rejected your application. It is categorised as a Read tool in the Vivioo MCP Server, which means it retrieves data without modifying state.
Register the Vivioo MCP server in PolicyLayer and add a rule for check_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 Vivioo. Nothing to install.
check_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_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_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_notifications is provided by the Vivioo MCP server (vivioo-io/vivioo-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 →