run_install · VibeServe MCP: Risk & Policy

WHAT IT DOES

What run_install does on VibeServe

AI agents invoke run_install to trigger actions in VibeServe. 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_install needs a policy

Package installation is a form of code execution that modifies system state irreversibly (packages persist until uninstalled). While not destructive in the sense of immediate data deletion, it runs commands whose effects depend on the argument (which package to install), making it Execute category.

From the tool's definition Tool description states 'Run package installation' — this directly executes system-level package management commands, which can modify the filesystem, install arbitrary code, and trigger external operations.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

run_install Rate-limited

run_install 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_install": {
      "limits": [
        {
          "counter": "run_install_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 VibeServe, so you can run agents against it safely.

FAQ

Questions about run_install

What does the run_install tool do? +

Run package installation. It is categorised as a Execute tool in the VibeServe 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_install? +

Register the VibeServe MCP server in PolicyLayer and add a rule for run_install: 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 VibeServe. Nothing to install.

What risk level is run_install? +

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

Can I rate-limit run_install? +

Yes. Add a rate_limit block to the run_install 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_install completely? +

Set action: deny in the PolicyLayer policy for run_install. 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_install? +

run_install is provided by the VibeServe MCP server (ncsound919/vibeserve). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.