AI agents invoke run_shell 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.
Shell execution is the highest-risk operation available to an AI agent outside of financial transactions. Any shell command can be run, including data destruction, system compromise, credential theft, lateral movement, or denial of service. Blast radius is unlimited and depends entirely on system permissions and agent behavior.
From the tool's definition Tool name 'run_shell' directly indicates shell command execution capability. Server description confirms 'command execution' among its capabilities. No description provided for the tool itself, but the name unambiguously denotes arbitrary code execution.
Documented attack patterns abuse exactly the kind of access run_shell 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_shell:
{
"version": "1",
"default": "deny",
"tools": {
"run_shell": {
"limits": [
{
"counter": "run_shell_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}run_shell 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_shell. 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_shell: 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_shell 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_shell 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_shell. 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_shell 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.