Drop orphaned embedding rows whose chunk_id no longer exists in
AI agents call vacuum_embeddings to permanently remove resources in Vault Memory — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool performs irreversible deletion of embedding data from the vault's index. While the rows being deleted are technically 'orphaned' (no longer referenced), the operation cannot be undone and permanently removes data. This makes it Destructive rather than Write. The high severity reflects that inadvertent or malicious use could corrupt the knowledge index and lose searchability for notes.
From the tool's definition Tool name 'vacuum_embeddings' combined with description stating 'Drop orphaned embedding rows' indicates irreversible deletion of database records. The word 'Drop' is explicit database terminology for permanent removal.
Attacks that exploit this kind of access
Drop orphaned embedding rows whose chunk_id no longer exists in. It is categorised as a Destructive tool in the Vault Memory MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Vault Memory MCP server in PolicyLayer and add a rule for vacuum_embeddings: 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 Vault Memory. Nothing to install.
vacuum_embeddings 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 vacuum_embeddings 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 vacuum_embeddings. 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.
vacuum_embeddings is provided by the Vault Memory MCP server (owrede/vault-memory). 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 →