Delete an entity from Datastore
AI agents call datastore_delete to permanently remove resources in MCP Datastore Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Deletion is an irreversible operation that destroys data without recovery options. Even though a single entity deletion may have limited blast radius compared to a mass delete, the Destructive category applies to any tool that removes data permanently.
From the tool's definition Tool name 'datastore_delete' and description 'Delete an entity from Datastore' indicate irreversible removal of data. This operation cannot be undone and permanently removes entities from the database.
Attacks that exploit this kind of access
Delete an entity from Datastore. It is categorised as a Destructive tool in the MCP Datastore Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the MCP Datastore Server MCP server in PolicyLayer and add a rule for datastore_delete: 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 Datastore Server. Nothing to install.
datastore_delete 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 datastore_delete 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 datastore_delete. 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.
datastore_delete is provided by the MCP Datastore Server MCP server (petekmet/mcp-gcp-datastore). 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 →