Execute DDL operations in Snowflake
AI agents call DDL_MANAGER to permanently remove resources in Snowflake Cortex AI MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
DDL (Data Definition Language) operations include CREATE, ALTER, DROP, TRUNCATE, and RENAME statements on database objects. These can irreversibly destroy or restructure database schemas, tables, and data. DROP or TRUNCATE operations in particular are irreversible and can cause catastrophic data loss at scale.
From the tool's definition Execute DDL operations in Snowflake
Attacks that exploit this kind of access
Execute DDL operations in Snowflake. It is categorised as a Destructive tool in the Snowflake Cortex AI MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Snowflake Cortex AI MCP Server MCP server in PolicyLayer and add a rule for DDL_MANAGER: 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 Cortex AI MCP Server. Nothing to install.
DDL_MANAGER 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 DDL_MANAGER 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 DDL_MANAGER. 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.
DDL_MANAGER is provided by the Snowflake Cortex AI MCP Server MCP server (sfc-gh-tgordonjr/mcp-snow-tg). 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 →