Delete a repl by ID (requires confirmation)
AI agents call delete_repl to permanently remove resources in Replit MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool irreversibly deletes an entire repl workspace and its associated data. While user confirmation is mentioned as a mitigation, the core action is permanent deletion, which is the defining characteristic of the Destructive category. The blast radius is high because an AI agent with access could destroy user projects, source code, and development environments.
From the tool's definition Tool name is 'delete_repl' and description states 'Delete a repl by ID'. The verb 'delete' combined with the action of removing a repl (a workspace environment) represents irreversible data destruction.
Attacks that exploit this kind of access
Delete a repl by ID (requires confirmation). It is categorised as a Destructive tool in the Replit MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Replit MCP Server MCP server in PolicyLayer and add a rule for delete_repl: 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 Replit MCP Server. Nothing to install.
delete_repl 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_repl 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_repl. 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_repl is provided by the Replit MCP Server MCP server (nova-3951/replit-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 →