chrome_evaluate_js
Runs arbitrary JavaScript in the current Google Chrome tab and returns its result. Requires 'Allow JavaScript from Apple Events' in Chrome's View → Developer menu.
This record as markdown: /tools/com-local-mcp-local-mcp/chrome-evaluate-js.md
What chrome_evaluate_js does on Local
AI agents invoke chrome_evaluate_js to trigger actions in Local. 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.
| Parameter | Type | Required | Description |
|---|---|---|---|
script | string | Yes |
Parameters from the server's own tool schema.
Why chrome_evaluate_js is rated High
Executing arbitrary JavaScript in a browser tab has an enormous blast radius: it can exfiltrate cookies/credentials, manipulate the DOM, make authenticated fetch requests to any origin the tab is logged into, redirect the page, install persistent scripts, and more. This is a code-execution primitive with critical severity.
From the tool's definition "Runs arbitrary JavaScript in the current Google Chrome tab" — executes arbitrary code in a live browser context
Risk signalsAccepts freeform code/query input (script)
Attacks that exploit this kind of access
The rule that runs chrome_evaluate_js safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Local, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For chrome_evaluate_js, this is the rule to start with:
chrome_evaluate_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.
The button opens the PolicyLayer dashboard: create your workspace, connect Local, apply this rule, and every chrome_evaluate_js call is checked against it from then on.
Questions about chrome_evaluate_js
Runs arbitrary JavaScript in the current Google Chrome tab and returns its result. Requires 'Allow JavaScript from Apple Events' in Chrome's View → Developer menu. It is categorised as a Execute tool in the Local MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
chrome_evaluate_js accepts 1 parameter: script. Required: script. The full parameter table on this page comes from the server's own tool schema.
Register the Local MCP server in PolicyLayer and add a rule for chrome_evaluate_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 Local. Nothing to install.
chrome_evaluate_js is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the chrome_evaluate_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.
Set action: deny in the PolicyLayer policy for chrome_evaluate_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.
chrome_evaluate_js is provided by the Local MCP server (local-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Local, and thousands of servers like it.
Across the catalogue