AI agents use create_acl_rule to create or update resources in Gcalendar — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Gcalendar environment.
This tool creates new sharing permissions without permanently deleting or destroying data. It is reversible (the accompanying 'delete_acl_rule' tool confirms this). While sharing does expose calendar data to additional users, the primary action is creating/modifying ACL rules (Write category), not reading data. It does not execute arbitrary code, move money, or irreversibly delete data.
From the tool's definition Tool description states 'Share a calendar with someone,' which creates a new access control rule (ACL) that grants permissions to another user. This modifies calendar sharing settings, which is a reversible write operation.
Attacks that exploit this kind of access
Share a calendar with someone. It is categorised as a Write tool in the Gcalendar MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Gcalendar MCP server in PolicyLayer and add a rule for create_acl_rule: 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 Gcalendar. Nothing to install.
create_acl_rule is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the create_acl_rule 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 create_acl_rule. 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.
create_acl_rule is provided by the Gcalendar MCP server (sandeepmallareddy/gcalendar-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 →