Execute a SQL query with read-only protection and flexible output format
AI agents invoke execute-query to trigger actions in Simple Snowflake 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.
SQL query execution is categorized as Execute because it runs code (SQL) against an external system (Snowflake) whose effects depend entirely on the query argument provided by an agent. Even with read-only protections in place, the tool executes arbitrary queries and interacts with external infrastructure.
From the tool's definition Tool name 'execute-query' combined with description stating it 'Execute[s] a SQL query' indicates code execution capability.
Documented attack patterns abuse exactly the kind of access execute-query gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Simple Snowflake MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for execute-query:
{
"version": "1",
"default": "deny",
"tools": {
"execute-query": {
"limits": [
{
"counter": "execute-query_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}execute-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 SQL query with read-only protection and flexible output format. It is categorised as a Execute tool in the Simple Snowflake MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Simple Snowflake MCP server in PolicyLayer and add a rule for execute-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 Simple Snowflake MCP. Nothing to install.
execute-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-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-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-query is provided by the Simple Snowflake MCP server (yannbrrd/simple_snowflake_mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Simple Snowflake MCP, 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.
8 Simple Snowflake MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.