Upload a file to the remote host via SFTP.
AI agents use ssh_upload to create or update resources in MCP Remote Access — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP Remote Access environment.
This tool performs file transfer that modifies the remote filesystem. While reversible (files can be deleted), it can upload malicious payloads, overwrite critical system files, or inject code into embedded systems. The high severity reflects the potential to compromise remote IoT/embedded devices through file injection.
From the tool's definition Tool description states 'Upload a file to the remote host via SFTP.' This creates or modifies data on a remote system.
Attacks that exploit this kind of access
Upload a file to the remote host via SFTP. It is categorised as a Write tool in the MCP Remote Access MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCP Remote Access MCP server in PolicyLayer and add a rule for ssh_upload: 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 MCP Remote Access. Nothing to install.
ssh_upload 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 ssh_upload 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_upload. 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_upload is provided by the MCP Remote Access MCP server (rfingadam/mcp-remote-access). 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 →