remove_cpg
AI agents call remove_cpg to permanently remove resources in CodeBadger — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The 'remove' verb combined with 'cpg' (Code Property Graph) indicates this tool deletes persistent analysis data. While the empty description prevents absolute certainty, the destructive nature of removal operations and the context of a static analysis server storing CPG state justify Destructive classification.
From the tool's definition Tool name 'remove_cpg' strongly suggests deletion or removal of the Code Property Graph data structure, which would irreversibly destroy analysis artifacts.
Attacks that exploit this kind of access
remove_cpg. It is categorised as a Destructive tool in the CodeBadger MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the CodeBadger MCP server in PolicyLayer and add a rule for remove_cpg: 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 CodeBadger. Nothing to install.
remove_cpg 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 remove_cpg 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 remove_cpg. 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.
remove_cpg is provided by the CodeBadger MCP server (lekssays/codebadger). 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 →