snowflake_execute_query · Integrations MCP: Risk & Policy

WHAT IT DOES

What snowflake_execute_query does on Integrations MCP

AI agents invoke snowflake_execute_query to trigger actions in Integrations 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.

WHY IT NEEDS A POLICY

Why snowflake_execute_query needs a policy

Snowflake query execution is a classic Execute category action—it runs code (SQL) whose effects depend entirely on the query argument. While the tool could theoretically be restricted to READ-only queries, the absence of qualifying language ('read-only', 'SELECT', etc.) and the use of 'execute_query' rather than 'run_select_query' suggests unrestricted query capability.

From the tool's definition Tool name 'snowflake_execute_query' indicates execution of arbitrary queries against Snowflake data warehouse. 'execute_query' is a hallmark Execute pattern.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

snowflake_execute_query Rate-limited

snowflake_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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "snowflake_execute_query": {
      "limits": [
        {
          "counter": "snowflake_execute_query_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Integrations MCP, so you can run agents against it safely.

FAQ

Questions about snowflake_execute_query

What does the snowflake_execute_query tool do? +

snowflake_execute_query. It is categorised as a Execute tool in the Integrations MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on snowflake_execute_query? +

Register the Integrations MCP server in PolicyLayer and add a rule for snowflake_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 Integrations MCP. Nothing to install.

What risk level is snowflake_execute_query? +

snowflake_execute_query is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit snowflake_execute_query? +

Yes. Add a rate_limit block to the snowflake_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.

How do I block snowflake_execute_query completely? +

Set action: deny in the PolicyLayer policy for snowflake_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.

What MCP server provides snowflake_execute_query? +

snowflake_execute_query is provided by the Integrations MCP server (shriram-vasudevan/integrations-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.