Delete a key-value pair from the store.
AI agents call delete_value to permanently remove resources in Simple MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently removes data from the key-value store without the ability to undo the operation. Deletion of data is irreversible and falls into the Destructive category. Severity is high because an AI agent could inadvertently delete critical stored values, and the in-memory nature suggests data loss cannot be recovered from backups once deleted.
From the tool's definition Tool name is 'delete_value' and description states 'Delete a key-value pair from the store.' The word 'delete' indicates irreversible removal of data.
Attacks that exploit this kind of access
Delete a key-value pair from the store. It is categorised as a Destructive tool in the Simple MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Simple MCP Server MCP server in PolicyLayer and add a rule for delete_value: 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 Simple MCP Server. Nothing to install.
delete_value 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 delete_value 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 delete_value. 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.
delete_value is provided by the Simple MCP Server MCP server (jmgress/simple-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 →