AI agents use ftp_put_contents to create or update resources in Ftp — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Ftp environment.
The tool creates or modifies data (file contents) on a remote system via FTP/SFTP. While it does not delete data (which would be Destructive), it can overwrite existing files with new content, making it a Write operation. Severity is high because unrestricted use could corrupt important remote files, modify application code, or inject malicious content on production servers.
From the tool's definition Tool description states: 'Write raw text directly to a remote destination.' This is a write operation that creates or modifies files on a remote FTP/SFTP server.
Attacks that exploit this kind of access
Write raw text directly to a remote destination. Best for creating NEW files. For modifying existing files, prefer ftp_patch_file. It is categorised as a Write tool in the Ftp MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Ftp MCP server in PolicyLayer and add a rule for ftp_put_contents: 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 Ftp. Nothing to install.
ftp_put_contents 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 ftp_put_contents 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 ftp_put_contents. 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.
ftp_put_contents is provided by the Ftp MCP server (kynlos/ftp-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 →