run_sql_query · Trip Planner MCP: Risk & Policy

WHAT IT DOES

What run_sql_query does on Trip Planner MCP

AI agents invoke run_sql_query to trigger actions in Trip Planner MCP. 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_sql_query needs a policy

SQL query execution is inherently an Execute category risk—it can trigger external operations with effects determined by query arguments. Without description details, we cannot confirm whether DELETE/DROP permissions exist (which would elevate to Destructive), but the capability to execute arbitrary queries against Postgres data represents significant blast radius if an AI agent submits malicious or unintended…

From the tool's definition Tool named 'run_sql_query' with empty description. Based on context, this server integrates Postgres data and enables multi-agent trip planning. A 'run_sql_query' tool permits arbitrary SQL execution against a database.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

run_sql_query Rate-limited

run_sql_query 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_sql_query": {
      "limits": [
        {
          "counter": "run_sql_query_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 Trip Planner MCP, so you can run agents against it safely.

FAQ

Questions about run_sql_query

What does the run_sql_query tool do? +

run_sql_query. It is categorised as a Execute tool in the Trip Planner MCP 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_sql_query? +

Register the Trip Planner MCP server in PolicyLayer and add a rule for run_sql_query: 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 Trip Planner MCP. Nothing to install.

What risk level is run_sql_query? +

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

Can I rate-limit run_sql_query? +

Yes. Add a rate_limit block to the run_sql_query 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_sql_query completely? +

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

run_sql_query is provided by the Trip Planner MCP server (sushruth3002/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.