AI agents invoke kde_notify to trigger actions in Sysprobe. 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.
The tool executes a system command (notify-send) to display a desktop notification. While the description says 'harmless, ungated', it is still an Execute action as it runs an external command with side effects visible to the user. The blast radius is low since notifications are ephemeral and non-destructive.
From the tool's definition 'Send a desktop notification (notify-send)' — triggers an external operation (notify-send command) on the desktop
Attacks that exploit this kind of access
Send a desktop notification (notify-send). Harmless, ungated. It is categorised as a Execute tool in the Sysprobe MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Sysprobe MCP server in PolicyLayer and add a rule for kde_notify: 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 Sysprobe. Nothing to install.
kde_notify 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 kde_notify 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 kde_notify. 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.
kde_notify is provided by the Sysprobe MCP server (raindancer118/sysprobe-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 →