A Chrome extension that exposes Chrome browser capabilities as an MCP server, enabling AI agents to control and interact with the browser
Critical failures across naming, descriptions, and schemas. Of 32 tools, only 2 (get_windows_and_tabs, performance_start_trace) have visible, complete schemas with descriptions. The remaining 30 tools show empty input schemas ({"type":"object","properties":{},"required":[]}) with no parameter documentation. Tool names lack consistency (chrome_read_page vs chrome_computer vs chrome_navigate, inconsistent prefixes). Descriptions range from adequate (chrome_read_page: 280 chars) to missing entirely (chrome_close_tabs, chrome_switch_tab, chrome_get_web_content show no descriptions in source). No output schemas documented. Error handling absent. Security concerns: chrome_inject_script, chrome_javascript, chrome_userscript expose arbitrary code execution without permission gates or audit trails.
Add a new bookmark
Delete a bookmark
Search bookmarks
Click on a specific element on the page
Close one or more tabs
Use a mouse and keyboard to interact with a web browser, and take screenshots. * Whenever you intend to click on an element like an icon, you should consult a read_page to determine the ref of the element before moving the cursor. * If you tried clicking on a program or link but it failed to load, even after waiting, try screenshot and then adjusting your click location so that the tip of the cursor visually falls on the element that you want to click. * Make sure to click any buttons, links, icons, etc with the cursor tip in the center of the element. Don't click boxes on their edges unless asked.
30 of 32 tools have empty input schemas (properties: {}, required: []) with zero parameter documentation.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 44 | 2026-07-28+ | v2 |
Access browser console
Fill form fields or select dropdown options
Get all interactive elements on the current page
Fetch and retrieve web content from a URL
Record page interactions as GIF
Handle browser dialogs (alert, confirm, prompt)
Handle file downloads
Access browser history
Inject JavaScript code into the page
Execute JavaScript in the page context
Send keyboard input to the browser
Navigate to a URL in the current or specified tab
Capture network requests and responses
Get an accessibility tree representation of visible elements on the page. Only returns elements that are visible in the viewport. Optionally filter for only interactive elements. Tip: If the returned elements do not include the specific element you need, use the computer tool's screenshot (action="screenshot") to capture the element's on-screen coordinates, then operate by coordinates.
Request user to select an element on the page
Take a screenshot of the current page
Send commands to previously injected scripts
Switch to a specific tab
Upload a file through the browser
Execute user scripts in the page
Get all currently open browser windows and tabs
Provides a lightweight summary of the last recorded trace. For deep insights (CWV, breakdowns), integrate native-side DevTools trace engine.
Starts a performance trace recording on the selected page. Optionally reloads the page and/or auto-stops after a short duration.
Stops the active performance trace recording on the selected page.
Run a recorded flow by ID with optional variables and run options. Returns a standardized run result.
Search for text content across open tabs
Missing descriptions for 25 tools (e.g., chrome_navigate, chrome_screenshot, chrome_close_tabs). Without one, LLMs cannot determine when or why to select the tool.' Description score capped at 0 for these.
Dangerous tools (chrome_inject_script, chrome_javascript, chrome_userscript) expose arbitrary code execution without permission gates, audit trails, or confirmation steps.
No output schemas documented for any tool.
Inconsistent naming conventions: chrome_* prefix used for most tools, but get_windows_and_tabs, performance_*, search_tabs_content, and record_replay_flow_run lack the prefix.