db_schedule_done · K-Personal MCP: Risk & Policy

WHAT IT DOES

What db_schedule_done does on K-Personal MCP

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

WHY IT NEEDS A POLICY

Why db_schedule_done needs a policy

This is a Write operation—it updates records in the personal SQLite database reversibly (the schedule state can be changed back). It does not delete data (ruling out Destructive) nor execute external code (ruling out Execute). The severity is medium because misuse could disrupt personal task/schedule tracking, but the blast radius is limited to one user's local database with no financial or external system impact.

From the tool's definition The tool name 'db_schedule_done' and description indicate it marks a schedule entry as complete, advancing recurring schedules to their next cycle or deactivating one-time schedules.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

db_schedule_done Rate-limited

db_schedule_done 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": {
    "db_schedule_done": {
      "limits": [
        {
          "counter": "db_schedule_done_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 K-Personal MCP, so you can run agents against it safely.

FAQ

Questions about db_schedule_done

What does the db_schedule_done tool do? +

일정 1건을 처리 완료로 표시. recur 면 next_run 을 다음 주기로 전진, 1회성이면 비활성화. It is categorised as a Write tool in the K-Personal MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on db_schedule_done? +

Register the K-Personal MCP server in PolicyLayer and add a rule for db_schedule_done: 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 K-Personal MCP. Nothing to install.

What risk level is db_schedule_done? +

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

Can I rate-limit db_schedule_done? +

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

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

db_schedule_done is provided by the K-Personal MCP server (lee30934-byte/k-personal-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.