Execute INSERT, UPDATE, or DELETE queries. Use for modifying data.
AI agents call execute_write to permanently remove resources in Google Services MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool explicitly supports DELETE queries in addition to INSERT and UPDATE, making it capable of irreversible data deletion. Since it can execute arbitrary DELETE statements, it falls under Destructive — the most severe applicable category. The blast radius is critical because a misused DELETE query (especially without a WHERE clause) could wipe entire tables or datasets irreversibly.
From the tool's definition Execute INSERT, UPDATE, or DELETE queries. Use for modifying data.
Attacks that exploit this kind of access
Execute INSERT, UPDATE, or DELETE queries. Use for modifying data. It is categorised as a Destructive tool in the Google Services MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Google Services MCP Server MCP server in PolicyLayer and add a rule for execute_write: 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 Google Services MCP Server. Nothing to install.
execute_write 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_write 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_write. 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_write is provided by the Google Services MCP Server MCP server (t4nm4ymittal/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 →