network_start

THE RISK

High Risk

Why network_start needs a policy

This tool initiates an active network monitoring/capture process within a stealth browser session. It triggers an ongoing external operation (packet/request interception) that affects browser behavior and can record sensitive request/response body data. This goes beyond passive reading — it starts a capture process with side effects, fitting the Execute category.

From the tool's definition Start capturing network requests. With capture_bodies=true also records request/response

Documented attack patterns abuse exactly the kind of access network_start gives an agent:

POLICY

How to control network_start

PolicyLayer is an MCP gateway — it sits between your AI agents and MCP Camoufox, and nothing reaches the server without passing your rules. This is the rule we recommend for network_start:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "network_start": {
      "limits": [
        {
          "counter": "network_start_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

network_start 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.

Create a free account and register MCP Camoufox — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

RATE-LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More MCP Camoufox tools

Destructive cookie_delete Delete cookies. Both empty = clear all. Destructive localstorage_clear Clear all localStorage. Destructive reset_profile Delete the persistent profile (~/.camoufox-mcp/profile) entirely. Destructive browser_close Close the browser. Cookies are preserved in the persistent profile (~/.camoufox-mcp/profil Destructive tab_close Close a tab by index (-1 = active), or by url_contains. Execute batch_actions Execute multiple actions in one call. Each action: {type, ref?, value?, text?, key?, url?} Execute browser_launch Launch Camoufox stealth browser and navigate to URL. Browser persists between calls. Execute evaluate Execute JavaScript in page context.

All 102 MCP Camoufox tools →

Execute tools on other servers

Android Forensics ADB MCP Server adb_shell_command EMBA-MCP run_emba_scan Frida Game Hacking MCP remove_breakpoint Procmon request_elevation

Go deeper

High-risk tools in MCP Camoufox → Every high-risk tool this server exposes, in one view.
All high-risk MCP tools → Every high-risk tool across the catalogue, and the policy pattern that contains them.
The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Agent sandbox → Bounding what an agent can execute and where the boundary should sit.
Least privilege for MCP → Granting agents the minimum tool surface the task needs.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about network_start

What does the network_start tool do? +

Start capturing network requests. With capture_bodies=true also records request/response. It is categorised as a Execute tool in the MCP Camoufox MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on network_start? +

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

What risk level is network_start? +

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

Can I rate-limit network_start? +

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

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

network_start is provided by the MCP Camoufox MCP server (robithyusuf/mcp-camoufox). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every MCP Camoufox tool call.

Start from MCP Camoufox, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →