Remove an article from the knowledge base by key.
AI agents call remove to permanently remove resources in Mcp Recall Md — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool deletes data from the knowledge base without the ability to undo the action. While not catastrophic in absolute terms (it's not financial or system-level), it permanently destroys stored information and intellectual content. The high severity reflects the irreversible nature of data loss and the potential impact on the user's knowledge base integrity.
From the tool's definition The tool description explicitly states it will "Remove an article from the knowledge base by key." This is an irreversible deletion operation—removed articles cannot be recovered.
Attacks that exploit this kind of access
Remove an article from the knowledge base by key. It is categorised as a Destructive tool in the Mcp Recall Md MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Mcp Recall Md MCP server in PolicyLayer and add a rule for remove: 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 Recall Md. Nothing to install.
remove 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 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. 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 is provided by the Mcp Recall Md MCP server (kalikin-artem/proj-mcp-recall-md). 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 →