get_execution_plan · Redshift MCP Server MCP: Risk & Policy

WHAT IT DOES

What get_execution_plan does on Redshift MCP Server

AI agents invoke get_execution_plan to trigger actions in Redshift 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 get_execution_plan needs a policy

An 'actual' execution plan (as opposed to an 'estimated' or 'explain-only' plan) requires the query to be run against the database to collect real runtime statistics. This means arbitrary SQL is executed, which could include data-modifying or destructive statements.

From the tool's definition 'Get actual execution plan with runtime statistics for a SQL query' — the word 'actual' indicates the query is actually executed (not just planned/estimated), running arbitrary SQL against the database

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

get_execution_plan Rate-limited

get_execution_plan 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": {
    "get_execution_plan": {
      "limits": [
        {
          "counter": "get_execution_plan_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 Redshift MCP Server, so you can run agents against it safely.

FAQ

Questions about get_execution_plan

What does the get_execution_plan tool do? +

Get actual execution plan with runtime statistics for a SQL query. It is categorised as a Execute tool in the Redshift 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 get_execution_plan? +

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

What risk level is get_execution_plan? +

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

Can I rate-limit get_execution_plan? +

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

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

get_execution_plan is provided by the Redshift MCP Server MCP server (moonlight-cl/redshift-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.