network_fail_request · CDP-MCP Server MCP: Risk & Policy

WHAT IT DOES

What network_fail_request does on CDP-MCP Server

AI agents invoke network_fail_request 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_fail_request needs a policy

This tool manipulates a live network request by causing it to fail, which is an active external operation that affects browser behavior and application logic. It doesn't merely read data, but triggers a side effect (request failure) that can disrupt application functionality. Since it operates on network interception (consistent with the server description mentioning 'network interception'), it falls under Execute.

From the tool's definition 'Fail a paused request with a specific error reason' — actively intercepts and aborts a network request in-flight

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

network_fail_request Rate-limited

network_fail_request 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_fail_request": {
      "limits": [
        {
          "counter": "network_fail_request_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_fail_request

What does the network_fail_request tool do? +

Fail a paused request with a specific error reason. 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_fail_request? +

Register the CDP-MCP Server MCP server in PolicyLayer and add a rule for network_fail_request: 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_fail_request? +

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

Can I rate-limit network_fail_request? +

Yes. Add a rate_limit block to the network_fail_request 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_fail_request completely? +

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

network_fail_request 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.