update_candidate · Kula Ai MCP: Risk & Policy

WHAT IT DOES

What update_candidate does on Kula Ai

AI agents use update_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 update_candidate needs a policy

This tool creates or modifies candidate data reversibly, fitting the Write category. Severity is high because modifying candidate information in a recruiting system could affect hiring decisions, candidate communications, and recruitment workflows. The tool operates on persistent data with business impact, though changes are not permanently destructive (candidates can be re-updated).

From the tool's definition Tool name is 'update_candidate' with description 'Update an existing candidate'. This modifies existing candidate data in the Kula recruiting API, which is reversible (can be updated again) but affects stored records.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

update_candidate Rate-limited

update_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": {
    "update_candidate": {
      "limits": [
        {
          "counter": "update_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 update_candidate

What does the update_candidate tool do? +

Update an existing candidate. 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 update_candidate? +

Register the Kula Ai MCP server in PolicyLayer and add a rule for update_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 update_candidate? +

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

Can I rate-limit update_candidate? +

Yes. Add a rate_limit block to the update_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 update_candidate completely? +

Set action: deny in the PolicyLayer policy for update_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 update_candidate? +

update_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.