zk_remove_link
AI agents call zk_remove_link to permanently remove resources in Zettelkasten — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Removing a link between notes is likely irreversible (or at least a destructive modification), as link relationships in a Zettelkasten system are typically not versioned. The sibling tool 'zk_create_link' creates links, while this tool removes them — the inverse operation.
From the tool's definition Tool name 'zk_remove_link' implies removal of a link between notes; the description is empty and uninformative, lowering confidence.
Attacks that exploit this kind of access
zk_remove_link. It is categorised as a Destructive tool in the Zettelkasten MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Zettelkasten MCP server in PolicyLayer and add a rule for zk_remove_link: 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 Zettelkasten. Nothing to install.
zk_remove_link 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 zk_remove_link 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 zk_remove_link. 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.
zk_remove_link is provided by the Zettelkasten MCP server (entanglr/zettelkasten-mcp). 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 →