删除计划
AI agents call delete_plan to permanently remove resources in Code Analysis MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool performs an irreversible operation (deletion) on stored plan data. While the blast radius is moderate because it only affects plan records rather than critical application data or financial systems, deletion cannot be undone and constitutes a destructive action. Confidence is reduced slightly due to minimal description, but the delete_ prefix leaves little ambiguity about the action's nature.
From the tool's definition Tool name is 'delete_plan' with description '删除计划' (Chinese for 'delete plan'). The verb 'delete' indicates irreversible removal of data.
Attacks that exploit this kind of access
删除计划. It is categorised as a Destructive tool in the Code Analysis MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Code Analysis MCP Server MCP server in PolicyLayer and add a rule for delete_plan: 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 Code Analysis MCP Server. Nothing to install.
delete_plan 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_plan 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_plan. 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_plan is provided by the Code Analysis MCP Server MCP server (zeocax/code-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 →