browser_evaluate
A execute tool on the Looking Glass MCP server.
This record as markdown: /tools/io-github-sahib-sawhney-wh-looking-glass-mcp/browser-evaluate.md
What browser_evaluate does on Looking Glass
AI agents invoke browser_evaluate to trigger actions in Looking Glass. 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 | JavaScript code to execute in the browser context |
Parameters from the server's own tool schema.
Why browser_evaluate is rated High
Tools named 'evaluate' in browser automation contexts (Playwright, Puppeteer, etc.) execute arbitrary JavaScript in the page context. This is an Execute-category action with critical severity because arbitrary code execution in a browser can exfiltrate data, manipulate DOM, steal credentials, or perform any action the browser can.
From the tool's definition Tool name 'browser_evaluate' strongly implies JavaScript evaluation/execution in a browser context; description is empty and uninformative.
Risk signalsAccepts freeform code/query input (script)
Attacks that exploit this kind of access
The rule that runs browser_evaluate safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Looking Glass, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For browser_evaluate, this is the rule to start with:
browser_evaluate 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 Looking Glass, apply this rule, and every browser_evaluate call is checked against it from then on.
Questions about browser_evaluate
browser_evaluate is a execute tool on the Looking Glass MCP server. It is categorised as a Execute tool in the Looking Glass MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
browser_evaluate accepts 1 parameter: script. Required: script. The full parameter table on this page comes from the server's own tool schema.
Register the Looking Glass MCP server in PolicyLayer and add a rule for browser_evaluate: 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 Looking Glass. Nothing to install.
browser_evaluate 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 browser_evaluate 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 browser_evaluate. 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.
browser_evaluate is provided by the Looking Glass MCP server (looking-glass-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Looking Glass, and thousands of servers like it.
Across the catalogue