start_proxy · Mitm MCP: Risk & Policy

WHAT IT DOES

What start_proxy does on Mitm

AI agents invoke start_proxy to trigger actions in Mitm. 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 start_proxy needs a policy

Starting a proxy interception session is an Execute action because it triggers an external operation (mitmproxy) whose effects depend on arguments (the engagement name) and configuration. The severity is critical because TLS interception can compromise confidentiality of all traffic from targeted devices, enable credential theft, and break security guarantees of encrypted communications.

From the tool's definition Tool 'start_proxy' initiates a mitmproxy interception session. The server description indicates this performs 'network-level TLS interception' to 'intercept traffic from devices', which involves launching an active proxy that intercepts and potentially…

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

start_proxy Rate-limited

start_proxy 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": {
    "start_proxy": {
      "limits": [
        {
          "counter": "start_proxy_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 Mitm, so you can run agents against it safely.

FAQ

Questions about start_proxy

What does the start_proxy tool do? +

Start a mitmproxy interception session for the named engagement. It is categorised as a Execute tool in the Mitm MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on start_proxy? +

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

What risk level is start_proxy? +

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

Can I rate-limit start_proxy? +

Yes. Add a rate_limit block to the start_proxy 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 start_proxy completely? +

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

start_proxy is provided by the Mitm MCP server (mplogas/mitmproxy-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.