AI agents call events_on to retrieve information from Webcal without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool lacks an explicit description, but contextual evidence strongly suggests it retrieves calendar events (likely filtered by a date or criterion based on the 'events_on' name). The server is explicitly read-only, and no modifying, executing, or destructive capabilities are evident. This is a data retrieval operation with no side effects.
From the tool's definition Tool name 'events_on' combined with server description stating it is 'read-only' and 'exposes iCalendar feeds as queryable tools' for 'calendar event retrieval and filtering.' Sibling tools (get_event, list_events, list_calendars) all indicate read-only…
Attacks that exploit this kind of access
events_on. It is categorised as a Read tool in the Webcal MCP Server, which means it retrieves data without modifying state.
Register the Webcal MCP server in PolicyLayer and add a rule for events_on: 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 Webcal. Nothing to install.
events_on 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 events_on 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 events_on. 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.
events_on is provided by the Webcal MCP server (mnot/webcal-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 →