AI agents call read_ssh_connections to retrieve information from Windows CLI MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves existing SSH connection configurations without modifying, deleting, or executing anything. It is a straightforward read operation that returns data about established connections. The low severity reflects minimal blast radius — an agent obtaining this information cannot directly compromise systems, though it could inform subsequent attacks if sensitive connection details are exposed.
From the tool's definition Tool name is 'read_ssh_connections' and description states 'Read all SSH connections' — a pure retrieval operation with no side effects.
Documented attack patterns abuse exactly the kind of access read_ssh_connections gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Windows CLI MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for read_ssh_connections:
{
"version": "1",
"default": "deny",
"tools": {
"read_ssh_connections": {}
}
}read_ssh_connections is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Read all SSH connections. It is categorised as a Read tool in the Windows CLI MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Windows CLI MCP Server MCP server in PolicyLayer and add a rule for read_ssh_connections: 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 Windows CLI MCP Server. Nothing to install.
read_ssh_connections is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the read_ssh_connections 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 read_ssh_connections. 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.
read_ssh_connections is provided by the Windows CLI MCP Server MCP server (simon-ami/win-cli-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 5 Windows CLI MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
5 Windows CLI MCP Server tools catalogued and risk-classified — across an index of 42,500+ MCP servers.