Remove agent with comprehensive cleanup and coordination
AI agents call delete_agent to permanently remove resources in Claude Code MCP - Agent Orchestration Platform — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently removes an agent and its related data structures. While the impact is scoped to a single agent entity rather than core infrastructure, the destruction is irreversible and could disrupt ongoing collaborative workflows.
From the tool's definition Tool name 'delete_agent' combined with description 'Remove agent with comprehensive cleanup and coordination' indicates irreversible deletion of an agent instance.
Attacks that exploit this kind of access
Remove agent with comprehensive cleanup and coordination. It is categorised as a Destructive tool in the Claude Code MCP - Agent Orchestration Platform MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Claude Code MCP - Agent Orchestration Platform MCP server in PolicyLayer and add a rule for delete_agent: 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 Claude Code MCP - Agent Orchestration Platform. Nothing to install.
delete_agent 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_agent 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_agent. 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_agent is provided by the Claude Code MCP - Agent Orchestration Platform MCP server (nexus-digital-automations/claude_code_mcp_2). 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 →