Run an artisan command in the Laravel directory
AI agents invoke run_artisan_command to trigger actions in Laravel Helpers MCP. 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.
Artisan is Laravel's command-line interface that can execute a wide range of operations—from reversible actions (create controllers, run migrations) to destructive ones (drop tables, purge caches). Since the tool permits running arbitrary Artisan commands without apparent restrictions, and the effects depend entirely on which command is passed, this is classified as Execute.
From the tool's definition Tool name 'run_artisan_command' and description 'Run an artisan command in the Laravel directory' indicates execution of arbitrary Artisan commands, which can trigger side effects including database migrations, code generation, or other system operations…
Documented attack patterns abuse exactly the kind of access run_artisan_command gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Laravel Helpers MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for run_artisan_command:
{
"version": "1",
"default": "deny",
"tools": {
"run_artisan_command": {
"limits": [
{
"counter": "run_artisan_command_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}run_artisan_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.
Run an artisan command in the Laravel directory. It is categorised as a Execute tool in the Laravel Helpers MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Laravel Helpers MCP server in PolicyLayer and add a rule for run_artisan_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 Laravel Helpers MCP. Nothing to install.
run_artisan_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 run_artisan_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 run_artisan_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.
run_artisan_command is provided by the Laravel Helpers MCP server (jsonallen/laravel-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Laravel Helpers MCP, 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.
4 Laravel Helpers MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.