execute_js

Execute arbitrary JS in the current page context or send JSON CDP bridge commands through the page bridge.

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/execute-js.md

WHAT IT DOES

What execute_js does on Agent Browser

AI agents invoke execute_js 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 execute_js is rated High

This tool permits execution of arbitrary code (JavaScript) within a live browser context that has access to login sessions, cookies, and sensitive user data as stated in the server description. An AI agent could use this to steal credentials, exfiltrate data, modify page content, perform unauthorized actions on behalf of the logged-in user, or pivot to other systems.

From the tool's definition Tool name 'execute_js' and description 'Execute arbitrary JS in the current page context' explicitly permits running arbitrary JavaScript code.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs execute_js 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 execute_js, this is the rule to start with:

execute_js Rate-limited

execute_js 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": {
    "execute_js": {
      "limits": [
        {
          "counter": "execute_js_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 execute_js call is checked against it from then on.

FAQ

Questions about execute_js

What does the execute_js tool do? +

Execute arbitrary JS in the current page context or send JSON CDP bridge commands through the page bridge. 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 execute_js? +

Register the Agent Browser MCP server in PolicyLayer and add a rule for execute_js: 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 execute_js? +

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

Can I rate-limit execute_js? +

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

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

execute_js 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

claude_execute on Claude Bridge →execute_test_case on Percepta MCP Server → All high-risk MCP tools → The MCP Attack Database →

Guides

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