AI agents use fs_apply_patch_with_backup to create or update resources in LocalAnt — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your LocalAnt environment.
This tool modifies file content (Write operation). Although it creates a backup for potential recovery, it irreversibly changes the current state of a file—a high-severity action if misapplied by an AI agent to critical system or application files.
From the tool's definition Tool name 'fs_apply_patch_with_backup' and description 'Replace an existing file' indicate modification of file contents. The '_with_backup' suffix suggests reversibility through backup restoration, distinguishing this from Destructive category.
Attacks that exploit this kind of access
Replace an existing file. It is categorised as a Write tool in the LocalAnt MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the LocalAnt MCP server in PolicyLayer and add a rule for fs_apply_patch_with_backup: 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 LocalAnt. Nothing to install.
fs_apply_patch_with_backup is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the fs_apply_patch_with_backup 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 fs_apply_patch_with_backup. 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.
fs_apply_patch_with_backup is provided by the LocalAnt MCP server (yuga-hashimoto/localant). 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 →