Trigger: User requests to remove a Knowledge Base from the project. Purpose: Remove a Knowledge Base association.
AI agents call remove_knowledge_base to permanently remove resources in MemOS — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool irreversibly removes a Knowledge Base from the project. While not a direct data deletion (which 'delete_kb_documents' appears to handle), removing/disassociating a Knowledge Base is a destructive action that cannot be easily reversed and would result in loss of access to stored information.
From the tool's definition Tool name contains 'remove' and description states 'Remove a Knowledge Base association.' The sibling tool 'delete_kb_documents' and 'delete_memory' confirm this server handles irreversible deletion operations.
Documented attack patterns abuse exactly the kind of access remove_knowledge_base gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MemOS, and nothing reaches the server without passing your rules. This is the rule we recommend for remove_knowledge_base:
{
"version": "1",
"default": "deny",
"hide": [
"remove_knowledge_base"
]
} remove_knowledge_base disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.
Free to start. No card required.
Trigger: User requests to remove a Knowledge Base from the project. Purpose: Remove a Knowledge Base association. It is categorised as a Destructive tool in the MemOS MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the MemOS MCP server in PolicyLayer and add a rule for remove_knowledge_base: 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 MemOS. Nothing to install.
remove_knowledge_base 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_knowledge_base 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_knowledge_base. 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_knowledge_base is provided by the MemOS MCP server (memtensor/memos-api-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MemOS, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
10 MemOS tools catalogued and risk-classified — across an index of 43,000+ MCP servers.