Remove a memory entry from the agent memory system
AI agents call remove_memory 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.
The tool performs an irreversible deletion operation on persistent agent memory. While the blast radius is somewhat contained (affects only one memory entry rather than entire database), the permanent loss of previously indexed semantic information and the inability to undo the action classify this as Destructive rather than Write.
From the tool's definition Tool name 'remove_memory' combined with description 'Remove a memory entry from the agent memory system' indicates irreversible deletion of stored data.
Attacks that exploit this kind of access
Remove a memory entry from the agent memory 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_memory: 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_memory 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_memory 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_memory. 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_memory 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 →