admin_reload_prompts · CloudNativePG MCP Server MCP

WHAT IT DOES

What admin_reload_prompts does on CloudNativePG MCP Server

AI agents invoke admin_reload_prompts to trigger actions in CloudNativePG 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 admin_reload_prompts needs a policy

This tool triggers an external operation (reloading configuration from a ConfigMap) rather than simply reading data or writing new data. It causes the server to re-fetch and apply prompt configuration, which is an execution-style action. Misconfiguration or malicious ConfigMap content could affect LLM behavior. Confidence is moderate because the description is brief and the full impact is not entirely clear.

From the tool's definition 'Reload prompts from the ConfigMap' — triggers an operational action that re-reads and applies configuration from a Kubernetes ConfigMap

Risk signalsAdmin/system-level operation

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

admin_reload_prompts Rate-limited

admin_reload_prompts 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": {
    "admin_reload_prompts": {
      "limits": [
        {
          "counter": "admin_reload_prompts_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 CloudNativePG MCP Server, so you can run agents against it safely.

FAQ

Questions about admin_reload_prompts

What does the admin_reload_prompts tool do? +

Reload prompts from the ConfigMap. It is categorised as a Execute tool in the CloudNativePG 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 admin_reload_prompts? +

Register the CloudNativePG MCP Server MCP server in PolicyLayer and add a rule for admin_reload_prompts: 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 CloudNativePG MCP Server. Nothing to install.

What risk level is admin_reload_prompts? +

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

Can I rate-limit admin_reload_prompts? +

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

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

admin_reload_prompts is provided by the CloudNativePG MCP Server MCP server (wateim/cnpg-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.