network_enable_interception · CDP-MCP Server MCP

WHAT IT DOES

What network_enable_interception does on CDP-MCP Server

AI agents invoke network_enable_interception to trigger actions in CDP-MCP Server. 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 network_enable_interception needs a policy

This tool activates network interception which pauses real network requests, enabling inspection and modification of traffic. It triggers an external browser-level operation with significant side effects: blocking page requests can cause pages to hang or fail. It doesn't merely read data — it intercepts and can modify live network traffic, qualifying as Execute.

From the tool's definition Enable network request interception (pauses matching requests for inspection/modification). WARNING: paused requests block the page.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

network_enable_interception Rate-limited

network_enable_interception 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": {
    "network_enable_interception": {
      "limits": [
        {
          "counter": "network_enable_interception_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 CDP-MCP Server, so you can run agents against it safely.

FAQ

Questions about network_enable_interception

What does the network_enable_interception tool do? +

Enable network request interception (pauses matching requests for inspection/modification). WARNING: paused requests block the page. It is categorised as a Execute tool in the CDP-MCP Server 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_enable_interception? +

Register the CDP-MCP Server MCP server in PolicyLayer and add a rule for network_enable_interception: 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 CDP-MCP Server. Nothing to install.

What risk level is network_enable_interception? +

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

Can I rate-limit network_enable_interception? +

Yes. Add a rate_limit block to the network_enable_interception 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_enable_interception completely? +

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

network_enable_interception is provided by the CDP-MCP Server MCP server (jekyll-001/cdp-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.