ssh_download_file

THE RISK

Low Risk

Why ssh_download_file needs a policy

This tool retrieves file content from a remote system without altering or deleting it. While classified as Read, severity is elevated to 'medium' rather than 'low' because: (1) an AI agent could download sensitive files if it obtains valid SSH credentials or access to an already-authenticated session, and (2) in the context of the sibling ssh_exec tool, downloaded files could contain credentials or secrets that…

From the tool's definition Tool name 'ssh_download_file' and description 'Download a file from the remote server' indicate retrieval of data without modification.

Documented attack patterns abuse exactly the kind of access ssh_download_file gives an agent:

POLICY

How to control ssh_download_file

PolicyLayer is an MCP gateway — it sits between your AI agents and SSH MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for ssh_download_file:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "ssh_download_file": {}
  }
}

ssh_download_file is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.

Create a free account and register SSH MCP — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

CAP THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More SSH MCP tools

Execute ssh_exec Execute a command on the remote server Execute ssh_connect Connect to a remote server via SSH Write ssh_upload_file Upload a file to the remote server Read ssh_list_files List files in a directory on the remote server Other ssh_disconnect Close an SSH connection

All 6 SSH MCP tools →

Read tools on other servers

M-Team MCP Server get_torrent_detail YouTube MCP Server search_channel Android Forensics ADB MCP Server parse_browser_history 0xarchive web3_challenge

Go deeper

The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Data exfiltration → How read access becomes an exfiltration channel when chained with untrusted content.
MCP token cost → What connecting this server costs in context-window tokens on every request.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about ssh_download_file

What does the ssh_download_file tool do? +

Download a file from the remote server. It is categorised as a Read tool in the SSH MCP MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on ssh_download_file? +

Register the SSH MCP server in PolicyLayer and add a rule for ssh_download_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 SSH MCP. Nothing to install.

What risk level is ssh_download_file? +

ssh_download_file is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit ssh_download_file? +

Yes. Add a rate_limit block to the ssh_download_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.

How do I block ssh_download_file completely? +

Set action: deny in the PolicyLayer policy for ssh_download_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.

What MCP server provides ssh_download_file? +

ssh_download_file is provided by the SSH MCP server (mixelpixx/ssh-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every SSH MCP tool call.

Start from SSH MCP, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →