Remove a file from the RAG system
AI agents call remove_file to permanently remove resources in MCP RAG — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently deletes files from the RAG system's vector database and storage. Once removed, the file and its associated embeddings cannot be recovered without external backups. This is a destructive operation that irreversibly removes data, making it more severe than a Write operation.
From the tool's definition Tool name is 'remove_file' and description states 'Remove a file from the RAG system'. The verb 'remove' combined with file deletion from a persistent vector storage system indicates irreversible deletion of data.
Attacks that exploit this kind of access
Remove a file from the RAG system. It is categorised as a Destructive tool in the MCP RAG MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the MCP RAG MCP server in PolicyLayer and add a rule for remove_file: 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 MCP RAG. Nothing to install.
remove_file 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 remove_file 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 remove_file. 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.
remove_file is provided by the MCP RAG MCP server (santis84/mcp-rag). 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 →