Critical-risk tools in Universal OpenAI Vector Store MCP Server
3 of the 21 tools in Universal OpenAI Vector Store MCP Server are classified as critical risk. This page profiles those tools specifically, with recommended policy actions and the attack patterns that target them.
Every operation listed below is an action PolicyLayer recommends controlling at the transport layer. Open any tool to see the full profile, risk score, and YAML policy snippet.
Tools at critical risk
-
file-deleteDestructivePermanently delete a file from your OpenAI account. This will remove the file from all vector stores and make it unavailable for future use. Use with caution as this action cann...
-
vector-store-deleteDestructiveDelete a vector store
-
vector-store-file-deleteDestructiveDelete a file from a vector store
Attacks that target this class
Critical-risk tools in any server share these documented attack patterns. Each links to the full case and the defensive policy.