Delete a flowPage block/model by UID. DESTRUCTIVE — also removes child blocks.
AI agents call destroy_flow_model to permanently remove resources in Nocobase — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently deletes flow models and their child blocks with no undo mechanism. The irreversible nature of deletion, combined with the cascade to child elements (increasing blast radius), makes this Destructive rather than Write.
From the tool's definition Tool name is 'destroy_flow_model' and description explicitly states 'Delete a flowPage block/model by UID.
Attacks that exploit this kind of access
Delete a flowPage block/model by UID. DESTRUCTIVE — also removes child blocks. It is categorised as a Destructive tool in the Nocobase MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Nocobase MCP server in PolicyLayer and add a rule for destroy_flow_model: 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 Nocobase. Nothing to install.
destroy_flow_model 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 destroy_flow_model 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 destroy_flow_model. 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.
destroy_flow_model is provided by the Nocobase MCP server (puguhsudarma/nocobase-mcp-server). 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 →