run_all_today · MCP Starter for Puch AI MCP: Risk & Policy

WHAT IT DOES

What run_all_today does on MCP Starter for Puch AI

AI agents invoke run_all_today to trigger actions in MCP Starter for Puch AI. 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 run_all_today needs a policy

This tool performs automated execution of visibility checks, which involves triggering external operations whose effects depend on the configured tracked queries. It is not merely reading data (would be Read if it only retrieved results), nor is it creating/modifying query configurations (would be Write). The 'Run' verb and 'automation helper' framing indicate it orchestrates execution of checks on multiple targets.

From the tool's definition 'Run visibility check for all tracked queries (helper for automation)' — the tool executes a visibility check operation across multiple tracked queries, triggering external monitoring/reporting actions.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

run_all_today Rate-limited

run_all_today 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": {
    "run_all_today": {
      "limits": [
        {
          "counter": "run_all_today_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 MCP Starter for Puch AI, so you can run agents against it safely.

FAQ

Questions about run_all_today

What does the run_all_today tool do? +

Run visibility check for all tracked queries (helper for automation). It is categorised as a Execute tool in the MCP Starter for Puch AI MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on run_all_today? +

Register the MCP Starter for Puch AI MCP server in PolicyLayer and add a rule for run_all_today: 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 MCP Starter for Puch AI. Nothing to install.

What risk level is run_all_today? +

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

Can I rate-limit run_all_today? +

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

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

run_all_today is provided by the MCP Starter for Puch AI MCP server (kulraj69/mcp-llm). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.