mark_explored · Kivv MCP: Risk & Policy

WHAT IT DOES

What mark_explored does on Kivv

AI agents use mark_explored to create or update resources in Kivv — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Kivv environment.

WHY IT NEEDS A POLICY

Why mark_explored needs a policy

This is a Write operation because it modifies data (paper status) reversibly. The agent could mark papers as explored incorrectly or inappropriately, affecting the library's organization, but the action is not destructive (reversible by unmarking). Severity is medium because misuse would disorganize the research library but cause no data loss or external impact.

From the tool's definition Tool description states 'Update a paper' which indicates a reversible modification operation. The tool modifies state (marking a paper as explored) without permanent deletion.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

mark_explored Rate-limited

mark_explored 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": {
    "mark_explored": {
      "limits": [
        {
          "counter": "mark_explored_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 Kivv, so you can run agents against it safely.

FAQ

Questions about mark_explored

What does the mark_explored tool do? +

Update a paper\. It is categorised as a Write tool in the Kivv MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on mark_explored? +

Register the Kivv MCP server in PolicyLayer and add a rule for mark_explored: 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 Kivv. Nothing to install.

What risk level is mark_explored? +

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

Can I rate-limit mark_explored? +

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

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

mark_explored is provided by the Kivv MCP server (jeffaf/kivv). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.