파일을 복사합니다. 덮어쓰기 전 대상 파일이 자동 백업됩니다.
AI agents use fm_copy_file to create or update resources in K-Personal MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your K-Personal MCP environment.
This tool modifies files reversibly through copying and automatic backup of overwritten files. While it affects data, the automatic backup mechanism means effects can be recovered, placing it in Write rather than Destructive. Medium severity due to potential for accidental overwriting of important files, though mitigated by the backup feature.
From the tool's definition fm_copy_file copies a file with automatic backup of the destination file before overwriting (파일을 복사합니다. 덮어쓰기 전 대상 파일이 자동 백업됩니다).
Attacks that exploit this kind of access
파일을 복사합니다. 덮어쓰기 전 대상 파일이 자동 백업됩니다. It is categorised as a Write tool in the K-Personal MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the K-Personal MCP server in PolicyLayer and add a rule for fm_copy_file: 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 K-Personal MCP. Nothing to install.
fm_copy_file 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 fm_copy_file 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 fm_copy_file. 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.
fm_copy_file is provided by the K-Personal MCP server (lee30934-byte/k-personal-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 →