执行写入 SQL（INSERT/UPDATE/DELETE/DDL）。
AI agents call write_sql to permanently remove resources in MCP Database Manager — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool executes arbitrary write SQL including DELETE and DDL statements, which can irreversibly destroy or alter schema and data across multiple databases. DDL operations like DROP TABLE or TRUNCATE are irreversible, placing this in the Destructive category. The blast radius is critical given multi-database access scope.
From the tool's definition 执行写入 SQL（INSERT/UPDATE/DELETE/DDL）— explicitly includes DELETE and DDL (DROP, ALTER, TRUNCATE) operations
Attacks that exploit this kind of access
执行写入 SQL（INSERT/UPDATE/DELETE/DDL）。. It is categorised as a Destructive tool in the MCP Database Manager MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the MCP Database Manager MCP server in PolicyLayer and add a rule for write_sql: 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 MCP Database Manager. Nothing to install.
write_sql 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_sql 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_sql. 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_sql is provided by the MCP Database Manager MCP server (meimingqi222/mcp-database-manager). 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 →