AI agents invoke run-command to trigger actions in Https://github Com/Streen9/react. 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.
Arbitrary terminal command execution is the highest-impact Execute risk. An AI agent given this tool could exfiltrate data, install malware, modify system files, or pivot to other systems. The lack of visible sandboxing or argument constraints on a React app development server makes this critical severity.
From the tool's definition Tool name 'run-command' with description 'Run a terminal command' explicitly permits arbitrary command execution. Sibling tools include package installation and process management, indicating this server operates with shell access.
Documented attack patterns abuse exactly the kind of access run-command gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Https://github Com/Streen9/react, and nothing reaches the server without passing your rules. This is the rule we recommend for run-command:
{
"version": "1",
"default": "deny",
"tools": {
"run-command": {
"limits": [
{
"counter": "run-command_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}run-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 a terminal command. It is categorised as a Execute tool in the Https://github Com/Streen9/react MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Https://github Com/Streen9/react MCP server in PolicyLayer and add a rule for run-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 Https://github Com/Streen9/react. Nothing to install.
run-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-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-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-command is provided by the Https://github Com/Streen9/react MCP server (kalivaraprasad-gonapa/react-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Https://github Com/Streen9/react, 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.
9 Https://github Com/Streen9/react tools catalogued and risk-classified — across an index of 43,000+ MCP servers.