remove_node
AI agents call remove_node to permanently remove resources in Dify MCP — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
A 'remove_node' operation in a workflow graph context would delete a node and potentially its associated edges, which is an irreversible destructive action. The description is empty, lowering confidence slightly, but the naming convention in context of sibling tools (all dealing with workflow node/edge creation) strongly suggests destructive deletion behavior.
From the tool's definition Tool name 'remove_node' strongly implies irreversible deletion of a node from a workflow. Context of sibling tools (add_answer_node, add_edge, add_end_node, etc.) confirms this operates on workflow graph elements.
Attacks that exploit this kind of access
remove_node. It is categorised as a Destructive tool in the Dify MCP MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Dify MCP server in PolicyLayer and add a rule for remove_node: 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 Dify MCP. Nothing to install.
remove_node 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_node 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_node. 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_node is provided by the Dify MCP server (taiki-kuraishi/dify-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 →