Get user's unread messages (requires privatemessages scope).
AI agents call get_unread_messages to retrieve information from PersonalizationMCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves private message data without modifying, deleting, or executing any actions. It is a Read operation because it only queries and returns existing data. However, severity is high because unread messages are sensitive personal communications that could contain private information, credentials, financial data, or other confidential content.
From the tool's definition Tool description explicitly states "Get user's unread messages" with "requires privatemessages scope". The verb 'Get' and the read-only nature of retrieving messages without modification indicates a Read operation.
Documented attack patterns abuse exactly the kind of access get_unread_messages gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and PersonalizationMCP, and nothing reaches the server without passing your rules. This is the rule we recommend for get_unread_messages:
{
"version": "1",
"default": "deny",
"tools": {
"get_unread_messages": {}
}
}get_unread_messages is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Get user's unread messages (requires privatemessages scope). It is categorised as a Read tool in the PersonalizationMCP MCP Server, which means it retrieves data without modifying state.
Register the Personalization MCP server in PolicyLayer and add a rule for get_unread_messages: 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 PersonalizationMCP. Nothing to install.
get_unread_messages 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 get_unread_messages 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 get_unread_messages. 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.
get_unread_messages is provided by the Personalization MCP server (yangliangwei/personalizationmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 88 PersonalizationMCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
88 PersonalizationMCP tools catalogued and risk-classified — across an index of 42,500+ MCP servers.