run_npx_command · Project Creator MCP: Risk & Policy

WHAT IT DOES

What run_npx_command does on Project Creator MCP

AI agents invoke run_npx_command to trigger actions in Project Creator 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.

WHY IT NEEDS A POLICY

Why run_npx_command needs a policy

Running npx commands allows arbitrary code execution in the project context. An AI agent could execute malicious npm packages, modify project dependencies, install backdoors, or chain calls with sibling delete_file tools for destructive operations. The critical severity reflects the potential for complete project compromise and lateral system impact.

From the tool's definition Tool name 'run_npx_command' indicates execution of npm/npx commands with arbitrary arguments. Sibling tools include 'delete_file' and file system operations, establishing this server's capability for destructive actions.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

run_npx_command Rate-limited

run_npx_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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "run_npx_command": {
      "limits": [
        {
          "counter": "run_npx_command_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Project Creator MCP, so you can run agents against it safely.

FAQ

Questions about run_npx_command

What does the run_npx_command tool do? +

run_npx_command. It is categorised as a Execute tool in the Project Creator MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on run_npx_command? +

Register the Project Creator MCP server in PolicyLayer and add a rule for run_npx_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 Project Creator MCP. Nothing to install.

What risk level is run_npx_command? +

run_npx_command is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit run_npx_command? +

Yes. Add a rate_limit block to the run_npx_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.

How do I block run_npx_command completely? +

Set action: deny in the PolicyLayer policy for run_npx_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.

What MCP server provides run_npx_command? +

run_npx_command is provided by the Project Creator MCP server (jackalterman/project-creator-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.