run_tsc · VibeServe MCP: Risk & Policy

WHAT IT DOES

What run_tsc does on VibeServe

AI agents invoke run_tsc 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_tsc needs a policy

run_tsc executes the TypeScript compiler, which is a command-line tool that processes code and produces output files (compiled JavaScript). Execution of external tools/commands falls under Execute category. The severity is high because uncontrolled compilation of arbitrary TypeScript code could expose secrets in source files, generate malicious output, or create unexpected side effects in a build pipeline.

From the tool's definition Tool name 'run_tsc' and description 'Run TypeScript compiler check' indicate execution of an external command (TypeScript compiler). This triggers compilation of code whose effects depend on the codebase being compiled.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

run_tsc Rate-limited

run_tsc 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_tsc": {
      "limits": [
        {
          "counter": "run_tsc_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_tsc

What does the run_tsc tool do? +

Run TypeScript compiler check. 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_tsc? +

Register the VibeServe MCP server in PolicyLayer and add a rule for run_tsc: 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_tsc? +

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

Can I rate-limit run_tsc? +

Yes. Add a rate_limit block to the run_tsc 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_tsc completely? +

Set action: deny in the PolicyLayer policy for run_tsc. 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_tsc? +

run_tsc 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.