Delete an edge
AI agents call delete_edge to permanently remove resources in AI Charts — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently deletes a diagram edge, which is an irreversible modification to the diagram structure. Although the impact is scoped to diagram metadata rather than production data, the destructive nature of deletion—combined with the absence of mention of built-in undo/recovery—places it in the Destructive category rather than Write.
From the tool's definition Tool name 'delete_edge' uses the verb 'delete', which irreversibly removes data (an edge/connection in a diagram). The description confirms this removes a diagram element that cannot be automatically recovered without undo functionality.
Attacks that exploit this kind of access
Delete an edge. It is categorised as a Destructive tool in the AI Charts MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the AI Charts MCP server in PolicyLayer and add a rule for delete_edge: 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 AI Charts. Nothing to install.
delete_edge 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 delete_edge 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 delete_edge. 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.
delete_edge is provided by the AI Charts MCP server (tjameswilliams/ai-charts). 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 →