get_sql

THE RISK

Low Risk

Why get_sql needs a policy

get_sql retrieves and displays SQL query strings generated by Cube.js without executing them or modifying any data. This is a read-only introspection capability with no side effects. Users can examine query logic but cannot trigger database operations, making it a low-severity Read tool suitable for understanding query generation and debugging.

From the tool's definition Tool returns generated SQL 'without executing it' - explicitly non-executable, purely informational retrieval

Documented attack patterns abuse exactly the kind of access get_sql gives an agent:

POLICY

How to control get_sql

PolicyLayer is an MCP gateway — it sits between your AI agents and Cube Js MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for get_sql:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "get_sql": {}
  }
}

get_sql is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.

Create a free account and register Cube Js MCP Server — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

CAP THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Cube Js MCP Server tools

Execute execute_query execute_query Execute execute_query_post Executes a query against the Cube.js API using POST method (recommended for complex querie Execute refresh Trigger a refresh for the given query (POST /refresh). Execute scheduled_refresh Trigger scheduled refresh (POST /refresh/schedule or similar). Execute raw_request Generic request tool to call arbitrary Cube.js REST endpoints. Execute refresh_pre_aggregations Refresh pre-aggregations (POST /pre-aggregations/refresh). Read check_health Checks the health status of the Cube.js server. Read get_schema Get the schema representation from Cube.js (GET /schema).

All 10 Cube Js MCP Server tools →

Read tools on other servers

M-Team MCP Server get_torrent_detail YouTube MCP Server search_channel Android Forensics ADB MCP Server parse_browser_history 0xarchive web3_challenge

Go deeper

The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Data exfiltration → How read access becomes an exfiltration channel when chained with untrusted content.
MCP token cost → What connecting this server costs in context-window tokens on every request.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about get_sql

What does the get_sql tool do? +

Returns the generated SQL for a given query without executing it. It is categorised as a Read tool in the Cube Js MCP Server MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on get_sql? +

Register the Cube Js MCP Server MCP server in PolicyLayer and add a rule for get_sql: 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 Cube Js MCP Server. Nothing to install.

What risk level is get_sql? +

get_sql is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit get_sql? +

Yes. Add a rate_limit block to the get_sql 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_sql completely? +

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

get_sql is provided by the Cube Js MCP Server MCP server (zsembek/cube.js-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Cube Js MCP Server tool call.

Start from Cube Js MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →