A Chrome extension that uses your own Chrome browser as an MCP server, enabling AI models to control and interact with Chrome through native messaging and HTTP transports
Critical failures across naming, descriptions, and schemas. 8 of 23 tools (35%) have completely empty input schemas with no properties or descriptions (chrome_keyboard, chrome_history, chrome_bookmark_search, chrome_bookmark_add, chrome_bookmark_delete, chrome_inject_script, chrome_send_command_to_inject_script, chrome_console, search_tabs_content). Descriptions are present but often generic or incomplete (e.g., 'Send keyboard input to the browser' with no detail on what input format is expected). No tool descriptions explain WHEN to use them vs. similar tools, or what the output structure is. No error handling guidance. No tool annotations (readOnlyHint, destructiveHint, idempotentHint) despite clear risk levels (DESTRUCTIVE, WRITE, READ_ONLY). Naming is inconsistent: 'chrome_' prefix is redundant given the server context; 'chrome_navigate' vs 'chrome_go_back_or_forward' lack parallel structure. No output schemas documented anywhere.
Add a bookmark
Delete a bookmark
Search browser bookmarks
Click on an element in the current page or at specific coordinates
Close one or more browser tabs
Execute JavaScript in the browser console
Fill a form element or select an option with the specified value
8 tools have completely empty input schemas (no properties, no required array, no descriptions).
No output schemas documented for any tool. LLMs cannot plan downstream calls or extract required fields (e.g., what does chrome_screenshot return? base64 string? file path? object with metadata?).
No tool annotations (readOnlyHint, destructiveHint, idempotentHint) despite clear risk levels declared (READ_ONLY, WRITE, DESTRUCTIVE). Agents cannot reason about side effects or retry safety.
Inferred effective spec: <=2025-11-25.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 45 | <=2025-11-25 | v2 |
Get interactive elements from the current page
Fetch content from a web page
Navigate back or forward in browser history
Access browser history
Inject and execute a script in the current page
Send keyboard input to the browser
Navigate to a URL or refresh the current tab
Start capturing network requests from a web page using Chrome webRequest API(without responseBody)
Stop capturing network requests using Chrome webRequest API and return the captured data
Start capturing network requests from a web page using Chrome Debugger API(with responseBody)
Stop capturing network requests using Chrome Debugger API and return the captured data
Send a network request from the browser with cookies and other browser context
Take a screenshot of the current page or a specific element(if you want to see the page, recommend to use chrome_get_web_content first)
Send a command to an injected script
Get all currently open browser windows and tabs
Search tab content using semantic similarity
Descriptions lack WHEN/WHY guidance. E.g., 'Send keyboard input to the browser' does not explain what input format is expected, when to use it vs. chrome_click_element, or what happens on error.
Redundant 'chrome_' prefix in all tool names. In a Chrome-specific server, this adds noise and violates verb_noun naming convention. Should be 'navigate', 'screenshot', 'click_element', etc.