Execute a command on the remote SSH server. Returns: JSON object with stdout, stderr, and exit code Use cases: - Run shell commands on remote servers - Check system status (uptime, disk space, processes) - Execute scripts or programs remotely - Manage services and applications
AI agents invoke ssh_execute to trigger actions in Playwright Stealth. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool executes arbitrary commands on a remote system via SSH. An AI agent given this tool could execute any command the SSH user has permission to run—including destructive commands (rm -rf /), exfiltrating data, installing malware, or compromising the server. While it could also perform read-only operations, its primary purpose and capability is unrestricted command execution.
From the tool's definition Tool description states "Execute a command on the remote SSH server" with use cases including "Run shell commands on remote servers" and "Execute scripts or programs remotely". Returns stdout, stderr, and exit code.
Documented attack patterns abuse exactly the kind of access ssh_execute gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Playwright Stealth, and nothing reaches the server without passing your rules. This is the rule we recommend for ssh_execute:
{
"version": "1",
"default": "deny",
"tools": {
"ssh_execute": {
"limits": [
{
"counter": "ssh_execute_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}ssh_execute 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.
Free to start. No card required.
Execute a command on the remote SSH server. Returns: JSON object with stdout, stderr, and exit code Use cases: - Run shell commands on remote servers - Check system status (uptime, disk space, processes) - Execute scripts or programs remotely - Manage services and applications. It is categorised as a Execute tool in the Playwright Stealth MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Playwright Stealth MCP server in PolicyLayer and add a rule for ssh_execute: 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 Playwright Stealth. Nothing to install.
ssh_execute is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the ssh_execute 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_execute. 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_execute is provided by the Playwright Stealth MCP server (pulsemcp/mcp-servers). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Playwright Stealth, 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.
68 Playwright Stealth tools catalogued and risk-classified — across an index of 43,000+ MCP servers.