Transfer a file between two connected remote servers (source → destination) via SFTP.
AI agents invoke ssh_transfer to trigger actions in Claude Ssh. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool moves files between remote servers, which is an active operation with external side effects beyond simple reads or writes. It can overwrite existing files on the destination server (potentially destructive), exfiltrate sensitive data between systems, or introduce malicious files. The cross-server nature increases blast radius.
From the tool's definition Transfer a file between two connected remote servers (source → destination) via SFTP
Attacks that exploit this kind of access
Transfer a file between two connected remote servers (source → destination) via SFTP. It is categorised as a Execute tool in the Claude Ssh MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Claude Ssh MCP server in PolicyLayer and add a rule for ssh_transfer: 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 Claude Ssh. Nothing to install.
ssh_transfer is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the ssh_transfer 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 ssh_transfer. 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.
ssh_transfer is provided by the Claude Ssh MCP server (marabank/mcp-ssh-server). 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 →