AI agents call poll_events to retrieve information from Loopsense without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves events that have occurred; it does not create, modify, delete, execute code, or move money. Even though it integrates with LoopSense's feedback monitoring system, the action is purely informational. Confidence is high because the verb 'Get' and the word 'fallback' explicitly indicate read-only retrieval.
From the tool's definition Tool description states 'Get new events since a timestamp' — a query operation that retrieves data without modification. The context (CI results, deployments, test outcomes) and 'push notification fallback' indicate passive polling of already-generated events.
Attacks that exploit this kind of access
Get new events since a timestamp (push notification fallback). It is categorised as a Read tool in the Loopsense MCP Server, which means it retrieves data without modifying state.
Register the Loopsense MCP server in PolicyLayer and add a rule for poll_events: 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 Loopsense. Nothing to install.
poll_events 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 poll_events 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 poll_events. 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.
poll_events is provided by the Loopsense MCP server (jarvisassistantux/loopsense). 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 →