AI agents invoke run_cmd to trigger actions in Allcanuse. 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.
A tool called 'run_cmd' almost certainly executes arbitrary shell commands on the local system (Windows/Linux as stated). This is Execute category because it triggers external operations whose effects depend entirely on the command arguments.
From the tool's definition Tool named 'run_cmd' with no description provided; server description explicitly mentions 'command execution' as a core capability; sibling tools include 'compile_c_program' and 'capture_screenshot' indicating system-level operations.
Documented attack patterns abuse exactly the kind of access run_cmd gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Allcanuse, and nothing reaches the server without passing your rules. This is the rule we recommend for run_cmd:
{
"version": "1",
"default": "deny",
"tools": {
"run_cmd": {
"limits": [
{
"counter": "run_cmd_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}run_cmd 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.
run_cmd. It is categorised as a Execute tool in the Allcanuse MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Allcanuse MCP server in PolicyLayer and add a rule for run_cmd: 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 Allcanuse. Nothing to install.
run_cmd 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 run_cmd 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 run_cmd. 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.
run_cmd is provided by the Allcanuse MCP server (ra1nyxin/allcanuse-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Allcanuse, 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.
130 Allcanuse tools catalogued and risk-classified — across an index of 43,000+ MCP servers.