evaluate_in_all_frames
Execute JavaScript code in all frames/iframes of the page. Args: code: JavaScript code to execute Returns: Results from all frames
This record as markdown: /tools/benjaminr-chrome-devtools-mcp/evaluate-in-all-frames.md
What evaluate_in_all_frames does on Chrome Devtools
AI agents invoke evaluate_in_all_frames to trigger actions in Chrome Devtools. 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 evaluate_in_all_frames is rated High
This tool permits execution of arbitrary JavaScript in all frames and iframes, giving an AI agent unfettered control over client-side behavior. An agent could steal credentials, manipulate the DOM, exfiltrate data, or perform actions on behalf of the user. The critical scope (all frames) and arbitrary code execution elevates this to critical severity.
From the tool's definition "Execute JavaScript code in all frames/iframes of the page" - the tool explicitly runs arbitrary JavaScript code across the entire DOM context, including nested frames.
Attacks that exploit this kind of access
The rule that runs evaluate_in_all_frames safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Chrome Devtools, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For evaluate_in_all_frames, this is the rule to start with:
evaluate_in_all_frames 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 Chrome Devtools, apply this rule, and every evaluate_in_all_frames call is checked against it from then on.
Questions about evaluate_in_all_frames
Execute JavaScript code in all frames/iframes of the page. Args: code: JavaScript code to execute Returns: Results from all frames. It is categorised as a Execute tool in the Chrome Devtools MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Chrome Devtools MCP server in PolicyLayer and add a rule for evaluate_in_all_frames: 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 Chrome Devtools. Nothing to install.
evaluate_in_all_frames 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 evaluate_in_all_frames 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 evaluate_in_all_frames. 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.
evaluate_in_all_frames is provided by the Chrome Devtools MCP server (benjaminr/chrome-devtools-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Chrome Devtools, and thousands of servers like it.
Across the catalogue