AI agents use backup_and_edit to create or update resources in Edit-MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Edit-MCP environment.
This tool creates backup copies of files, which is a reversible Write operation. It does not permanently delete data (not Destructive), execute arbitrary code (not Execute), or move money (not Financial). While backups are protective in intent, they create new files and modify the filesystem, placing them squarely in the Write category.
From the tool's definition Tool description states 'Create backups of files before editing them', indicating file creation/modification operations. The term 'backup' implies copying/duplicating file data into new locations.
Attacks that exploit this kind of access
Create backups of files before editing them. It is categorised as a Write tool in the Edit-MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Edit- MCP server in PolicyLayer and add a rule for backup_and_edit: 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 Edit-MCP. Nothing to install.
backup_and_edit 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 backup_and_edit 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 backup_and_edit. 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.
backup_and_edit is provided by the Edit- MCP server (mixelpixx/microsoft-edit-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 →