close_requisition · Kula Ai MCP: Risk & Policy

WHAT IT DOES

What close_requisition does on Kula Ai

AI agents use close_requisition 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.

WHY IT NEEDS A POLICY

Why close_requisition needs a policy

Closing a requisition changes its status but does not permanently delete data or prevent reversal (the requisition can typically be reopened). This makes it a Write operation rather than Destructive. While it affects recruiting workflow, it lacks financial transaction semantics and is not Execute (no arbitrary code/command).

From the tool's definition Tool description states 'Close a requisition', which modifies the state of a requisition record from an open/active state to closed. This is a reversible state change on a data resource.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

close_requisition Rate-limited

close_requisition stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "close_requisition": {
      "limits": [
        {
          "counter": "close_requisition_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Kula Ai, so you can run agents against it safely.

FAQ

Questions about close_requisition

What does the close_requisition tool do? +

Close a requisition. Only requisitions in a closeable state can be closed. 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.

How do I enforce a policy on close_requisition? +

Register the Kula Ai MCP server in PolicyLayer and add a rule for close_requisition: 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.

What risk level is close_requisition? +

close_requisition is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit close_requisition? +

Yes. Add a rate_limit block to the close_requisition 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.

How do I block close_requisition completely? +

Set action: deny in the PolicyLayer policy for close_requisition. 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.

What MCP server provides close_requisition? +

close_requisition 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.