Execute a query and stream results to a file at a chosen path.
AI agents invoke execute_query_to_file to trigger actions in Snowflake 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.
This tool both executes queries (which could include destructive SQL despite the server's 'read-only' claim) and writes to arbitrary file paths on the filesystem. The combination of query execution and file-system write access elevates this beyond a simple Read or Write operation. An AI agent could misuse this to exfiltrate data to attacker-controlled paths or overwrite sensitive files.
From the tool's definition 'Execute a query and stream results to a file at a chosen path' — runs arbitrary queries AND writes output to a filesystem path chosen by the caller
Documented attack patterns abuse exactly the kind of access execute_query_to_file gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Snowflake MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for execute_query_to_file:
{
"version": "1",
"default": "deny",
"tools": {
"execute_query_to_file": {
"limits": [
{
"counter": "execute_query_to_file_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
} execute_query_to_file 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 query and stream results to a file at a chosen path. It is categorised as a Execute tool in the Snowflake MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Snowflake MCP Server MCP server in PolicyLayer and add a rule for execute_query_to_file: 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 Snowflake MCP Server. Nothing to install.
execute_query_to_file 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_query_to_file 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_query_to_file. 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_query_to_file is provided by the Snowflake MCP Server MCP server (ncejda-g2/snowflake_mcp_server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Snowflake MCP Server, 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.
7 Snowflake MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.