cdp_send · Browser CDP MCP Server MCP: Risk & Policy

WHAT IT DOES

What cdp_send does on Browser CDP MCP Server

AI agents invoke cdp_send to trigger actions in Browser 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 cdp_send needs a policy

CDP (Chrome DevTools Protocol) allows arbitrary execution of browser commands including running JavaScript, accessing file system, network interception, navigating to arbitrary URLs, and more.

From the tool's definition Tool name 'cdp_send' on a server described as providing 'direct access to Chrome DevTools Protocol' with 'execution of any CDP command for flexible browser control'

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

cdp_send Rate-limited

cdp_send 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": {
    "cdp_send": {
      "limits": [
        {
          "counter": "cdp_send_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 Browser CDP MCP Server, so you can run agents against it safely.

FAQ

Questions about cdp_send

What does the cdp_send tool do? +

cdp_send. It is categorised as a Execute tool in the Browser 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 cdp_send? +

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

What risk level is cdp_send? +

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

Can I rate-limit cdp_send? +

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

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

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