AI agents call recent_notifications to retrieve information from Wardrowbe without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves notification history without creating, modifying, deleting, or executing operations. It is a pure read operation with minimal blast radius—exposing historical notifications poses low security risk even if misused by an AI agent.
From the tool's definition Tool name 'recent_notifications' and description 'List recent push/Mattermost notifications' indicate a retrieval operation with no modification or side effects. The limit parameter (1-100) is a standard pagination control.
Attacks that exploit this kind of access
List recent push/Mattermost notifications. limit 1–100. It is categorised as a Read tool in the Wardrowbe MCP Server, which means it retrieves data without modifying state.
Register the Wardrowbe MCP server in PolicyLayer and add a rule for recent_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 Wardrowbe. Nothing to install.
recent_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 recent_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 recent_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.
recent_notifications is provided by the Wardrowbe MCP server (saya6k/mcp-wardrowbe). 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 →