Orchestrator tool that:
AI agents call clean_repository_history to permanently remove resources in GitHub Auditor MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This is an orchestrator that coordinates destructive sibling tools. Purging and scrubbing Git history, squashing commits, and removing files from history are irreversible operations. Once history is rewritten and force-pushed, the original state cannot be recovered without a prior backup.
From the tool's definition 'clean_repository_history' orchestrates multiple operations including 'purge_history', 'scrub_ignored_files', and 'squash_noise_commits' — all of which irreversibly modify or destroy Git history
Attacks that exploit this kind of access
Orchestrator tool that:. It is categorised as a Destructive tool in the GitHub Auditor MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the GitHub Auditor MCP Server MCP server in PolicyLayer and add a rule for clean_repository_history: 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 GitHub Auditor MCP Server. Nothing to install.
clean_repository_history 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 clean_repository_history 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 clean_repository_history. 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.
clean_repository_history is provided by the GitHub Auditor MCP Server MCP server (westkevin12/repo-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 →