run_biome · VibeServe MCP: Risk & Policy

WHAT IT DOES

What run_biome does on VibeServe

AI agents invoke run_biome 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_biome needs a policy

This tool executes an external linter/formatter (Biome) which processes code files. While formatting is typically reversible, the tool executes arbitrary external processes whose effects depend on configuration and target files. This falls under Execute rather than Write because it invokes a complex external tool rather than directly creating/modifying data through the MCP interface.

From the tool's definition Tool runs Biome linter/formatter, a code analysis and transformation tool that executes external processes on files with potential side effects (formatting changes, file modifications).

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

run_biome Rate-limited

run_biome 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_biome": {
      "limits": [
        {
          "counter": "run_biome_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_biome

What does the run_biome tool do? +

Run Biome linter/formatter. 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_biome? +

Register the VibeServe MCP server in PolicyLayer and add a rule for run_biome: 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_biome? +

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

Can I rate-limit run_biome? +

Yes. Add a rate_limit block to the run_biome 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_biome completely? +

Set action: deny in the PolicyLayer policy for run_biome. 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_biome? +

run_biome 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.