AI agents use upload to create or update resources in Ssh — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Ssh environment.
File upload creates or modifies files on a remote system, which is a Write operation rather than Read (retrieves data) or Destructive (irreversible deletion). Severity is high because an AI agent uploading malicious scripts, configuration files, or sensitive data to production servers could cause significant damage, though it remains reversible (files can be deleted).
From the tool's definition Tool uploads file to connected server. Although the description is brief, the name 'upload' and verb phrase 'upload file to' indicate data creation/modification on a remote system.
Attacks that exploit this kind of access
Upload file to connected server. It is categorised as a Write tool in the Ssh MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Ssh MCP server in PolicyLayer and add a rule for 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 Ssh. Nothing to install.
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 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 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.
upload is provided by the Ssh MCP server (zachflint/ssh-mcp-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 →