AI agents call ssh_plan to retrieve information from MCP SSH Orchestrator without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool only displays what a command would do and whether policy permits it, producing no side effects. It is analogous to a 'plan' or 'dry-run' command (e.g., terraform plan), which is purely informational. Severity is low because misuse only reveals planned operations and policy configuration, not execute them.
From the tool's definition 'Show what would be executed and if policy allows' — this is a dry-run/preview operation that reads and evaluates policy without actually executing anything
Documented attack patterns abuse exactly the kind of access ssh_plan gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP SSH Orchestrator, and nothing reaches the server without passing your rules. This is the rule we recommend for ssh_plan:
{
"version": "1",
"default": "deny",
"tools": {
"ssh_plan": {}
}
}ssh_plan 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.
Show what would be executed and if policy allows. It is categorised as a Read tool in the MCP SSH Orchestrator MCP Server, which means it retrieves data without modifying state.
Register the MCP SSH Orchestrator MCP server in PolicyLayer and add a rule for ssh_plan: 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 MCP SSH Orchestrator. Nothing to install.
ssh_plan 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 ssh_plan 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_plan. 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_plan is provided by the MCP SSH Orchestrator MCP server (samerfarida/mcp-ssh-orchestrator). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MCP SSH Orchestrator, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
13 MCP SSH Orchestrator tools catalogued and risk-classified — across an index of 43,000+ MCP servers.