Execute an INSERT, UPDATE, or DELETE query on the Snowflake database
AI agents call write_query to permanently remove resources in Snowflake MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool explicitly supports DELETE operations, which irreversibly remove data from the database. It also supports INSERT and UPDATE, but since DELETE is permitted and the most severe applicable category applies, this is classified as Destructive. An AI agent misusing this tool could wipe entire tables or corrupt critical production data, warranting critical severity.
From the tool's definition Execute an INSERT, UPDATE, or DELETE query on the Snowflake database
Attacks that exploit this kind of access
Execute an INSERT, UPDATE, or DELETE query on the Snowflake database. It is categorised as a Destructive tool in the Snowflake MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Snowflake MCP Server MCP server in PolicyLayer and add a rule for write_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 Snowflake MCP Server. Nothing to install.
write_query is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the write_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 write_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.
write_query is provided by the Snowflake MCP Server MCP server (tushar3006/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →