create_candidate · Kula Ai MCP: Risk & Policy

WHAT IT DOES

What create_candidate does on Kula Ai

AI agents use create_candidate 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 create_candidate needs a policy

This tool creates and persists new data (candidate records) in the recruitment system, which is a reversible write operation. While it doesn't delete or destroy data (Destructive), doesn't execute arbitrary code (Execute), and doesn't move money (Financial), it does create new records that can theoretically be modified or removed later.

From the tool's definition Tool description states 'Create a new candidate' which performs a create operation that modifies data in the Kula recruiting system by adding a new candidate record.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

create_candidate Rate-limited

create_candidate 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": {
    "create_candidate": {
      "limits": [
        {
          "counter": "create_candidate_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 create_candidate

What does the create_candidate tool do? +

Create a new candidate in Kula. At least one of email or linkedin_url (in social_urls) is required. 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 create_candidate? +

Register the Kula Ai MCP server in PolicyLayer and add a rule for create_candidate: 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 create_candidate? +

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

Can I rate-limit create_candidate? +

Yes. Add a rate_limit block to the create_candidate 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 create_candidate completely? +

Set action: deny in the PolicyLayer policy for create_candidate. 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 create_candidate? +

create_candidate 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.