Executes a SQL query on a Nile database
AI agents invoke execute-sql to trigger actions in Nile. 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 allows execution of SQL queries whose effects depend entirely on the query argument provided. While SQL queries can be read-only (SELECT), write-based (INSERT, UPDATE), or destructive (DELETE, DROP), the tool permits all types. An AI agent with access to this tool could accidentally or maliciously execute destructive queries like DROP TABLE or DELETE without restrictions.
From the tool's definition Tool name 'execute-sql' with description 'Executes a SQL query on a Nile database' indicates it runs arbitrary SQL queries against a database.
Documented attack patterns abuse exactly the kind of access execute-sql gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Nile, and nothing reaches the server without passing your rules. This is the rule we recommend for execute-sql:
{
"version": "1",
"default": "deny",
"tools": {
"execute-sql": {
"limits": [
{
"counter": "execute-sql_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}execute-sql 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.
Executes a SQL query on a Nile database. It is categorised as a Execute tool in the Nile MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Nile MCP server in PolicyLayer and add a rule for execute-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 Nile. Nothing to install.
execute-sql 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-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.
Set action: deny in the PolicyLayer policy for execute-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.
execute-sql is provided by the Nile MCP server (@niledatabase/nile-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Nile, 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.
11 Nile tools catalogued and risk-classified — across an index of 43,000+ MCP servers.