Clean build artifacts.
AI agents call cargo_clean to permanently remove resources in Cargo MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
cargo clean deletes the target directory and all compiled build artifacts. While these files can be regenerated by rebuilding, the deletion itself is irreversible (files are removed from disk). This qualifies as Destructive. Severity is medium because only build artifacts are lost, not source code, but rebuilding can take significant time and resources.
From the tool's definition 'cargo_clean' and 'Clean build artifacts' — removing build artifacts is an irreversible deletion of generated files
Attacks that exploit this kind of access
Clean build artifacts. It is categorised as a Destructive tool in the Cargo MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Cargo MCP Server MCP server in PolicyLayer and add a rule for cargo_clean: 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 Cargo MCP Server. Nothing to install.
cargo_clean 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 cargo_clean 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 cargo_clean. 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.
cargo_clean is provided by the Cargo MCP Server MCP server (seemethere/cargo-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 →