dev.preflight · MCP: Risk & Policy

WHAT IT DOES

What dev.preflight does on Mcp

AI agents invoke dev.preflight to trigger actions in 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 dev.preflight needs a policy

This tool processes and evaluates shell commands (curl/wget/httpie) and makes outbound HTTP requests to external URLs. Even framed as a 'preflight check,' it actively parses and executes or triggers network operations against arbitrary URLs, which constitutes external execution. The ability to fire arbitrary HTTP methods against any target URL represents significant blast radius if misused by an agent.

From the tool's definition Check whether a shell command is runnable before running it — a pre-execution gate for agent-generated commands. POST command (curl/wget/httpie or anything with a URL). Parses out method, target URL, and headers

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

dev.preflight Rate-limited

dev.preflight 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": {
    "dev.preflight": {
      "limits": [
        {
          "counter": "dev.preflight_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 Mcp, so you can run agents against it safely.

FAQ

Questions about dev.preflight

What does the dev.preflight tool do? +

Check whether a shell command is runnable before running it — a pre-execution gate for agent-generated commands. POST command (curl/wget/httpie or anything with a URL). Parses out method, target URL, and headers and returns a structured verdict: verdict (. It is categorised as a Execute tool in the 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 dev.preflight? +

Register the MCP server in PolicyLayer and add a rule for dev.preflight: 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 Mcp. Nothing to install.

What risk level is dev.preflight? +

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

Can I rate-limit dev.preflight? +

Yes. Add a rate_limit block to the dev.preflight 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 dev.preflight completely? +

Set action: deny in the PolicyLayer policy for dev.preflight. 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 dev.preflight? +

dev.preflight is provided by the MCP server (@2sio/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.