AI agents invoke test_notification to trigger actions in Run402. 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 actively triggers a real notification through the system pipeline, which constitutes executing an external operation. While marked as a test (is_test=true) and rate-limited, it still causes side effects in external systems (notification delivery, audit row creation).
From the tool's definition 'Trigger a real test notification' and 'Verifies the full pipeline end-to-end' indicate this runs an actual external operation (sending a notification through the full pipeline), not just reading data.
Attacks that exploit this kind of access
Trigger a real test notification (audit row marked is_test=true). Rate-limited per wallet at 1/min. Verifies the full pipeline end-to-end. It is categorised as a Execute tool in the Run402 MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Run402 MCP server in PolicyLayer and add a rule for test_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 Run402. Nothing to install.
test_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 test_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 test_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.
test_notification is provided by the Run402 MCP server (kychee-com/run402). 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 →