start_capture · Mitm MCP: Risk & Policy

WHAT IT DOES

What start_capture does on Mitm

AI agents invoke start_capture 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_capture needs a policy

This tool triggers an external operation (packet capture) whose effects depend on arguments (choice of interface, duration, filters). While ostensibly for security testing, it enables interception of sensitive network traffic including credentials and API keys, making it an Execute-category risk.

From the tool's definition Tool 'start_capture' initiates packet capture on a network interface using tshark, which is a network packet analysis tool that intercepts live traffic.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

start_capture Rate-limited

start_capture 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_capture": {
      "limits": [
        {
          "counter": "start_capture_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_capture

What does the start_capture tool do? +

Start tshark packet capture on an interface for a session. 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_capture? +

Register the Mitm MCP server in PolicyLayer and add a rule for start_capture: 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_capture? +

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

Can I rate-limit start_capture? +

Yes. Add a rate_limit block to the start_capture 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_capture completely? +

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

start_capture 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.