This record as markdown: /tools/0xyg3n-claude-c2/rm.md
What rm does on Claude C2
AI agents call rm to permanently remove resources in Claude C2, typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Why rm is rated Critical
File and directory deletion is inherently destructive and cannot be undone. Given the MCP context where an AI agent could invoke this tool based on natural language commands, a misused 'rm' command could delete critical system files, user data, or entire directory structures across the connected remote system. This represents maximum severity due to irreversibility and potential for widespread unintended data loss.
From the tool's definition Tool name 'rm' combined with description 'Delete file/directory' directly indicates irreversible removal of files or directories. The 'Auto-selects client' phrasing suggests it operates across the remote system without requiring explicit path confirmation.
Attacks that exploit this kind of access
The rule that runs rm safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Claude C2, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For rm, this is the rule to start with:
rm is removed from the agent's tool list entirely, so the agent never calls it. The rest of the server keeps working.
The button opens the PolicyLayer dashboard: create your workspace, connect Claude C2, apply this rule, and every rm call is checked against it from then on.
Questions about rm
Delete file/directory. Auto-selects client. It is categorised as a Destructive tool in the Claude C2 MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Claude C2 MCP server in PolicyLayer and add a rule for rm: 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 C2. Nothing to install.
rm 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 rm 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 rm. 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.
rm is provided by the Claude C2 MCP server (0xyg3n/claude-c2). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Claude C2, and thousands of servers like it.
Across the catalogue