cdp_batch

Run a CDP bridge batch command; pass the full JSON command object as text.

SERVERAgent Browser SOURCE335234131/agent-browser-mcp

High RISK CLASS

Category Execute

Parameters 00 required

Recommended Rate-limitedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/335234131-agent-browser-mcp/cdp-batch.md

WHAT IT DOES

What cdp_batch does on Agent Browser

AI agents invoke cdp_batch to trigger actions in Agent Browser. 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.

RISK

Why cdp_batch is rated High

cdp_batch executes external operations (CDP commands) whose effects are entirely argument-dependent and can modify browser state, intercept traffic, manipulate the DOM, or exfiltrate sensitive data from authenticated sessions. This is Execute rather than Write because CDP commands are system-level browser control operations that go beyond simple data creation/modification.

From the tool's definition Tool enables direct execution of Chrome DevTools Protocol (CDP) commands via JSON objects. CDP provides low-level control over browser state, navigation, DOM manipulation, and network interception.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs cdp_batch safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Agent Browser, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For cdp_batch, this is the rule to start with:

cdp_batch Rate-limited

cdp_batch 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_batch": {
      "limits": [
        {
          "counter": "cdp_batch_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Agent Browser, apply this rule, and every cdp_batch call is checked against it from then on.

FAQ

Questions about cdp_batch

What does the cdp_batch tool do? +

Run a CDP bridge batch command; pass the full JSON command object as text. It is categorised as a Execute tool in the Agent Browser 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_batch? +

Register the Agent Browser MCP server in PolicyLayer and add a rule for cdp_batch: 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 Agent Browser. Nothing to install.

What risk level is cdp_batch? +

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

Can I rate-limit cdp_batch? +

Yes. Add a rate_limit block to the cdp_batch 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_batch completely? +

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

cdp_batch is provided by the Agent Browser MCP server (335234131/agent-browser-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Agent Browser, and thousands of servers like it.

This server

All 20 Agent Browser tools → High-risk tools on this server →

Across the catalogue

qt_batch on Qt → All high-risk MCP tools → The MCP Attack Database →

Guides

Govern code and CI agents →Agent sandbox →Least privilege for MCP →