Execute a natural language query on the SQL database
AI agents invoke execute_nl_query to trigger actions in SQLGenius. 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.
This tool translates arbitrary natural language into SQL and executes it against a live BigQuery database. Because the generated SQL is not constrained to read-only SELECT statements, it could produce INSERT, UPDATE, DELETE, DROP, or other destructive operations depending on how the NL-to-SQL translation works.
From the tool's definition "Execute a natural language query on the SQL database" — the tool executes queries derived from natural language input against a BigQuery database.
Documented attack patterns abuse exactly the kind of access execute_nl_query gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and SQLGenius, and nothing reaches the server without passing your rules. This is the rule we recommend for execute_nl_query:
{
"version": "1",
"default": "deny",
"tools": {
"execute_nl_query": {
"limits": [
{
"counter": "execute_nl_query_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}execute_nl_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.
Free to start. No card required.
Execute a natural language query on the SQL database. It is categorised as a Execute tool in the SQLGenius MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the SQLGenius MCP server in PolicyLayer and add a rule for execute_nl_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 SQLGenius. Nothing to install.
execute_nl_query is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the execute_nl_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.
Set action: deny in the PolicyLayer policy for execute_nl_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.
execute_nl_query is provided by the SQLGenius MCP server (pawankumar94/sql_mcp_server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from SQLGenius, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
4 SQLGenius tools catalogued and risk-classified — across an index of 43,000+ MCP servers.