Write data to a file, COMPLETELY REPLACING it if it exists.
AI agents call write_file_overwrite to permanently remove resources in File Writer — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Overwriting a file destroys the previous content permanently. Unlike append or safe-write operations, this tool obliterates existing data, making it Destructive. The blast radius is high because an AI agent could overwrite any file within the root directory, losing data that may be critical and unrecoverable.
From the tool's definition 'COMPLETELY REPLACING it if it exists' — the original file content is irreversibly overwritten with no recovery path unless a separate backup is made.
Attacks that exploit this kind of access
Write data to a file, COMPLETELY REPLACING it if it exists. It is categorised as a Destructive tool in the File Writer MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the File Writer MCP server in PolicyLayer and add a rule for write_file_overwrite: 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 File Writer. Nothing to install.
write_file_overwrite 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 write_file_overwrite 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 write_file_overwrite. 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.
write_file_overwrite is provided by the File Writer MCP server (thekogit/file_writer_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 →