Execute a DDL or DML statement (INSERT, UPDATE, DELETE, CREATE, DROP, etc.).
AI agents call execute_statement to permanently remove resources in Tdsql — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool explicitly supports DROP (irreversible table/database destruction), DELETE (irreversible data removal), as well as DDL operations like CREATE that can overwrite schemas. Because it permits the most severe irreversible operations (DROP, DELETE), it must be classified as Destructive.
From the tool's definition Execute a DDL or DML statement (INSERT, UPDATE, DELETE, CREATE, DROP, etc.)
Documented attack patterns abuse exactly the kind of access execute_statement gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Tdsql, and nothing reaches the server without passing your rules. This is the rule we recommend for execute_statement:
{
"version": "1",
"default": "deny",
"hide": [
"execute_statement"
]
}execute_statement disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.
Free to start. No card required.
Execute a DDL or DML statement (INSERT, UPDATE, DELETE, CREATE, DROP, etc.). It is categorised as a Destructive tool in the Tdsql MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Tdsql MCP server in PolicyLayer and add a rule for execute_statement: 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 Tdsql. Nothing to install.
execute_statement 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 execute_statement 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_statement. 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_statement is provided by the Tdsql MCP server (ksturgeon-td/tdsql-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Tdsql, 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 Tdsql tools catalogued and risk-classified — across an index of 43,000+ MCP servers.