ssh_session_start

THE RISK

High Risk

Why ssh_session_start needs a policy

This tool initiates an interactive remote shell session via SSH, allowing arbitrary command execution on a remote system. The blast radius is critical because an AI agent with access to this tool could execute any command the SSH user account permits on the target system, potentially compromising systems, exfiltrating data, modifying configurations, or launching further attacks.

From the tool's definition Tool description states 'Start an interactive SSH session with PTY' which enables remote command execution on SSH targets. The server description explicitly mentions 'enables secure remote command execution via SSH'.

Documented attack patterns abuse exactly the kind of access ssh_session_start gives an agent:

POLICY

How to control ssh_session_start

PolicyLayer is an MCP gateway — it sits between your AI agents and SSH MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for ssh_session_start:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "ssh_session_start": {
      "limits": [
        {
          "counter": "ssh_session_start_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

ssh_session_start stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

Create a free account and register SSH MCP Server — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

RATE-LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More SSH MCP Server tools

Destructive remove_credential Remove a stored SSH credential Execute ssh_exec Execute command over SSH using stored credentials Execute ssh_exec_raw Execute command over SSH with array arguments that are safely quoted for the remote shell Execute ssh_session_end End an interactive SSH session Execute ssh_tunnel_start Start an SSH tunnel for port forwarding Execute ssh_tunnel_stop Stop an SSH tunnel Execute rsync_copy Copy files/directories between local and remote server via rsync (best for directories or Execute ssh_session_send Send input to an interactive SSH session

All 15 SSH MCP Server tools →

Execute tools on other servers

Android Forensics ADB MCP Server adb_shell_command EMBA-MCP run_emba_scan Frida Game Hacking MCP remove_breakpoint Procmon request_elevation

Go deeper

High-risk tools in SSH MCP Server → Every high-risk tool this server exposes, in one view.
All high-risk MCP tools → Every high-risk tool across the catalogue, and the policy pattern that contains them.
The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Agent sandbox → Bounding what an agent can execute and where the boundary should sit.
Least privilege for MCP → Granting agents the minimum tool surface the task needs.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about ssh_session_start

What does the ssh_session_start tool do? +

Start an interactive SSH session with PTY (for vim, htop, etc). It is categorised as a Execute tool in the SSH MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on ssh_session_start? +

Register the SSH MCP Server MCP server in PolicyLayer and add a rule for ssh_session_start: 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. Nothing to install.

What risk level is ssh_session_start? +

ssh_session_start is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit ssh_session_start? +

Yes. Add a rate_limit block to the ssh_session_start 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.

How do I block ssh_session_start completely? +

Set action: deny in the PolicyLayer policy for ssh_session_start. 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.

What MCP server provides ssh_session_start? +

ssh_session_start is provided by the SSH MCP Server MCP server (kinothe-kafkaesque/ssh-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every SSH MCP Server tool call.

Start from SSH MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →