Upload a file via SFTP
AI agents use ssh_upload_file to create or update resources in Ssh Mcp Server Secured — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Ssh Mcp Server Secured environment.
The tool creates or modifies files on remote systems via SFTP, which is a reversible write operation. Severity is high because uploaded files could overwrite critical system files, configuration files, or application code on remote servers, potentially compromising system integrity or enabling follow-on attacks.
From the tool's definition Tool name 'ssh_upload_file' and description 'Upload a file via SFTP' indicate file creation/modification on remote servers without deletion.
Attacks that exploit this kind of access
Upload a file via SFTP. It is categorised as a Write tool in the Ssh Mcp Server Secured MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Ssh Mcp Server Secured MCP server in PolicyLayer and add a rule for ssh_upload_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 Server Secured. Nothing to install.
ssh_upload_file 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_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.
Set action: deny in the PolicyLayer policy for ssh_upload_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.
ssh_upload_file is provided by the Ssh Mcp Server Secured MCP server (marian-craciunescu/ssh-mcp-server-secured). 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 →