deleteCollection
AI agents call deleteCollection to permanently remove resources in RAG MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The Destructive category applies because this tool deletes entire data collections—an operation that cannot be undone and eliminates all associated embeddings and documents. While the description is empty (lowering confidence slightly), the function name is unambiguous and the context of a document/collection management server makes the destructive intent clear.
From the tool's definition Tool name 'deleteCollection' indicates irreversible deletion of data. Combined with the server's purpose of managing ChromaDB vector collections and documents, this tool would permanently remove a collection and its embedded PDF data without the ability to…
Attacks that exploit this kind of access
deleteCollection. It is categorised as a Destructive tool in the RAG MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the RAG MCP Server MCP server in PolicyLayer and add a rule for deleteCollection: 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 RAG MCP Server. Nothing to install.
deleteCollection 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 deleteCollection 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 deleteCollection. 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.
deleteCollection is provided by the RAG MCP Server MCP server (nsantra/rag-mcp-server). 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 →