AI agents call eventGet to retrieve information from Routine without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves calendar event information without side effects. It follows the standard GET pattern for querying existing data. The minimal description suggests a simple retrieval operation consistent with other Read tools on the server (calendarGet, pageGet, peopleGet, eventDay, eventTimeline). No creation, modification, deletion, code execution, or financial activity is implied.
From the tool's definition Tool name 'eventGet' and description 'An event' indicate a retrieval operation. The verb 'Get' combined with the read-only nature of fetching calendar event data without modification.
Attacks that exploit this kind of access
An event. It is categorised as a Read tool in the Routine MCP Server, which means it retrieves data without modifying state.
Register the Routine MCP server in PolicyLayer and add a rule for eventGet: 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 Routine. Nothing to install.
eventGet 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 eventGet 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 eventGet. 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.
eventGet is provided by the Routine MCP server (routineco/mcp-server). 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 →