scheduler_start | PolicyLayer

WHAT IT DOES

What scheduler_start does on PM-MCP (Portfolio Management MCP Server)

AI agents invoke scheduler_start to trigger actions in PM-MCP (Portfolio Management MCP Server). What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why scheduler_start needs a policy

Starting a scheduler that controls automated portfolio management operations, backtesting, report generation, and market monitoring represents an Execute-level risk. An AI agent triggering this without proper constraints could activate unintended automated trades, analysis runs, or data operations across the portfolio system.

From the tool's definition Tool name 'scheduler_start' indicates activation of a scheduling system. The Korean description '스케줄러 시작' translates to 'Start scheduler', confirming this initiates automated execution of scheduled tasks.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

scheduler_start Rate-limited

scheduler_start stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "scheduler_start": {
      "limits": [
        {
          "counter": "scheduler_start_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches PM-MCP (Portfolio Management MCP Server), so you can run agents against it safely.

FAQ

Questions about scheduler_start

What does the scheduler_start tool do? +

스케줄러 시작. It is categorised as a Execute tool in the PM-MCP (Portfolio Management MCP Server) MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on scheduler_start? +

Register the PM-MCP (Portfolio Management MCP Server) MCP server in PolicyLayer and add a rule for scheduler_start: 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 PM-MCP (Portfolio Management MCP Server). Nothing to install.

What risk level is scheduler_start? +

scheduler_start is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit scheduler_start? +

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

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

scheduler_start is provided by the PM-MCP (Portfolio Management MCP Server) MCP server (surplus96/pm-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.