run_semgrep · VibeServe MCP: Risk & Policy

WHAT IT DOES

What run_semgrep does on VibeServe

AI agents invoke run_semgrep 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_semgrep needs a policy

This tool executes Semgrep, a static analysis security scanner, which is an external operation that runs code analysis processes. While SAST scanning itself is typically safe (non-destructive, read-focused analysis), the 'run' verb and the invocation of an external analysis engine classifies it as Execute rather than Read, since it triggers a subprocess/system operation whose scope and side effects (report…

From the tool's definition Run Semgrep SAST scan on the project — executes a static analysis security tool on project code, which triggers external operations and generates reports whose effects depend on the scan scope and project state.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

run_semgrep Rate-limited

run_semgrep 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_semgrep": {
      "limits": [
        {
          "counter": "run_semgrep_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_semgrep

What does the run_semgrep tool do? +

Run Semgrep SAST scan on the project. 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_semgrep? +

Register the VibeServe MCP server in PolicyLayer and add a rule for run_semgrep: 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_semgrep? +

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

Can I rate-limit run_semgrep? +

Yes. Add a rate_limit block to the run_semgrep 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_semgrep completely? +

Set action: deny in the PolicyLayer policy for run_semgrep. 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_semgrep? +

run_semgrep 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.