AI agents call revert_to_version to permanently remove resources in CodeSavant — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Reverting to a specific version irreversibly overwrites the current file content. Any work done after that version is lost unless separately preserved. This is a destructive overwrite operation. While a history mechanism exists on this server, the act of reverting itself discards the current state non-reversibly in typical version-control semantics, placing it in the Destructive category.
From the tool's definition 'Revert a code file to a specific version' — overwrites the current file state with a prior version, discarding all changes made since that version.
Documented attack patterns abuse exactly the kind of access revert_to_version gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and CodeSavant, and nothing reaches the server without passing your rules. This is the rule we recommend for revert_to_version:
{
"version": "1",
"default": "deny",
"hide": [
"revert_to_version"
]
}revert_to_version disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.
Free to start. No card required.
Revert a code file to a specific version. It is categorised as a Destructive tool in the CodeSavant MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the CodeSavant MCP server in PolicyLayer and add a rule for revert_to_version: 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 CodeSavant. Nothing to install.
revert_to_version 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 revert_to_version 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 revert_to_version. 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.
revert_to_version is provided by the CodeSavant MCP server (twolven/mcp-codesavant). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from CodeSavant, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
7 CodeSavant tools catalogued and risk-classified — across an index of 43,000+ MCP servers.