AI agents use create_interview to create or update resources in Kula Ai — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Kula Ai environment.
This tool creates and modifies scheduling state within the recruiting system. While it has side effects (calendar invites sent, conference URLs generated), these are reversible through the cancel_interview tool. It does not execute arbitrary code, delete data irreversibly, or move money.
From the tool's definition Tool name is 'create_interview' and description states 'Schedule an interview' — this creates a new calendar event and provisions resources (calendar invites, conference URL).
Attacks that exploit this kind of access
Schedule an interview against an application. Calendar invites and conference URL are provisioned asynchronously — subscribe to the. It is categorised as a Write tool in the Kula Ai MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Kula Ai MCP server in PolicyLayer and add a rule for create_interview: 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 Kula Ai. Nothing to install.
create_interview 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_interview 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_interview. 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_interview is provided by the Kula Ai MCP server (kula-ai/kula-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 →