Save FTP/SFTP/SSH server credentials to the user
AI agents use add_server to create or update resources in Otoinstall — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Otoinstall environment.
This tool is classified as Write rather than Execute or Destructive because it stores credentials without immediately executing operations or deleting data. However, severity is elevated to 'high' because compromised server credentials could enable unauthorized access to infrastructure, making this a high-impact Write operation. Confidence is 0.95 due to the clear description explicitly mentioning credential storage.
From the tool's definition The tool description states 'Save FTP/SFTP/SSH server credentials to the user', which involves storing sensitive authentication credentials. This creates new data (credential entries) in a reversible manner.
Attacks that exploit this kind of access
Save FTP/SFTP/SSH server credentials to the user. It is categorised as a Write tool in the Otoinstall MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Otoinstall MCP server in PolicyLayer and add a rule for add_server: 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 Otoinstall. Nothing to install.
add_server 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 add_server 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 add_server. 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.
add_server is provided by the Otoinstall MCP server (otoinstall-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 →