Execute a command synchronously inside a browser VM. Returns stdout, stderr, and exit code. The command field is the executable; use args for its arguments. Common uses: read files (command:
AI agents invoke exec_command to trigger actions in Kernel MCP Server. 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 allows running arbitrary shell commands within a browser VM, making it Execute (not Read) because it can trigger any external operation or side effect depending on arguments. The critical severity reflects that an AI agent could misuse this to execute destructive commands (rm, dd, etc.), exfiltrate data, pivot to other systems, install malware, or modify system state.
From the tool's definition 'Execute a command synchronously inside a browser VM' with full stdout/stderr/exit code output capability. Tool explicitly performs arbitrary command execution within a virtual machine environment.
Documented attack patterns abuse exactly the kind of access exec_command gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Kernel MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for exec_command:
{
"version": "1",
"default": "deny",
"tools": {
"exec_command": {
"limits": [
{
"counter": "exec_command_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}exec_command 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 synchronously inside a browser VM. Returns stdout, stderr, and exit code. The command field is the executable; use args for its arguments. Common uses: read files (command:. It is categorised as a Execute tool in the Kernel MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Kernel MCP Server MCP server in PolicyLayer and add a rule for exec_command: 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 Kernel MCP Server. Nothing to install.
exec_command 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 exec_command 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 exec_command. 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.
exec_command is provided by the Kernel MCP Server MCP server (kernel/kernel-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Kernel MCP Server, 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.
16 Kernel MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.