Delete conversation data
AI agents call delete_blob to permanently remove resources in MemoDB MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool performs an irreversible delete operation on conversation data ('blobs'). Destructive operations that cannot be undone are classified as more severe than Write operations. While the blast radius depends on what blob is targeted, the ability to permanently erase conversation context and personal knowledge represents a high-severity risk if invoked by an AI agent without proper authorization or validation.
From the tool's definition Tool name 'delete_blob' combined with description 'Delete conversation data' indicates irreversible deletion of stored data.
Attacks that exploit this kind of access
Delete conversation data. It is categorised as a Destructive tool in the MemoDB MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the MemoDB MCP Server MCP server in PolicyLayer and add a rule for delete_blob: 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 MemoDB MCP Server. Nothing to install.
delete_blob 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_blob 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_blob. 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_blob is provided by the MemoDB MCP Server MCP server (wuyunmei/momedb-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 →