AI agents call get_interview_plan to retrieve information from Kula Ai without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries existing interview plan configuration data (stages and pre-configured activities) without creating, modifying, deleting, or executing anything. It is a straightforward read operation with minimal security risk - the worst case exposure would be access to internal recruiting process information.
From the tool's definition The description explicitly states 'Read the interview plan configured on a job' - this is a retrieval operation that accesses pre-configured interview data with no modifications or side effects.
Attacks that exploit this kind of access
Read the interview plan configured on a job — stages with their pre-configured interview activities. It is categorised as a Read tool in the Kula Ai MCP Server, which means it retrieves data without modifying state.
Register the Kula Ai MCP server in PolicyLayer and add a rule for get_interview_plan: 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.
get_interview_plan 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 get_interview_plan 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 get_interview_plan. 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.
get_interview_plan 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 →