ssh_upload · Langfuse Observability MCP: Risk & Policy

WHAT IT DOES

What ssh_upload does on Langfuse Observability

AI agents use ssh_upload to create or update resources in Langfuse Observability — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Langfuse Observability environment.

WHY IT NEEDS A POLICY

Why ssh_upload needs a policy

This tool creates or writes files on a remote system, which is reversible (files can be deleted or overwritten). While it doesn't execute code directly, uploading scripts for remote execution creates the precondition for Execute operations. The severity is high because misconfiguration or malicious file uploads could compromise remote systems, introduce vulnerabilities, or enable lateral movement.

From the tool's definition Tool description states 'Upload a file from the local machine to the remote SSH server via SFTP' and use cases include 'Deploy configuration files to servers' and 'Upload scripts for remote execution'. The tool modifies remote state by creating/writing files.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

ssh_upload Rate-limited

ssh_upload stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "ssh_upload": {
      "limits": [
        {
          "counter": "ssh_upload_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Langfuse Observability, so you can run agents against it safely.

FAQ

Questions about ssh_upload

What does the ssh_upload tool do? +

Upload a file from the local machine to the remote SSH server via SFTP. Returns: Success message with transfer details Use cases: - Deploy configuration files to servers - Upload scripts for remote execution - Transfer data files for processing. It is categorised as a Write tool in the Langfuse Observability MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on ssh_upload? +

Register the Langfuse Observability 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 Langfuse Observability. Nothing to install.

What risk level is ssh_upload? +

ssh_upload is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit ssh_upload? +

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.

How do I block ssh_upload completely? +

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.

What MCP server provides ssh_upload? +

ssh_upload is provided by the Langfuse Observability MCP server (langfuse-observability-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.