AI agents invoke send-notification to trigger actions in MCPing. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
Sending a desktop notification is an external operation that interacts with the macOS notification system. It is not a simple data read or write; it executes a system action that surfaces UI to the user, could be used for phishing/social engineering, or spam the user with misleading alerts.
From the tool's definition 'Send a desktop notification on macOS with icon, image, and sound customization' — triggers an external operation (system-level desktop notification) with user-visible side effects
Attacks that exploit this kind of access
Send a desktop notification on macOS with icon, image, and sound customization. It is categorised as a Execute tool in the MCPing MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the MCPing MCP server in PolicyLayer and add a rule for send-notification: 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 MCPing. Nothing to install.
send-notification is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the send-notification 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 send-notification. 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.
send-notification is provided by the MCPing MCP server (toolprint/mcping-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 →