Chronos Browser
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| browser_launchB | Launch or verify Chrome browser in the background. Set focus=True only if you explicitly want to bring it to the foreground. |
| browser_focusC | Explicitly bring the browser window to the foreground. |
| browser_statusB | Check browser status, active tabs, and CDP connection state. |
| browser_navigateC | Navigate a tab to the specified URL. |
| browser_clickC | Click an element identified by CSS selector, text, XPath, aria-label, title, or placeholder. |
| browser_typeC | Type or fill text into an input, textarea, or contenteditable element. |
| browser_press_keyC | Press a keyboard key (e.g. Enter, Escape, Tab, Backspace, ArrowDown). |
| browser_scrollC | Scroll page up, down, top, bottom, or by specific pixel amount. |
| browser_get_contentC | Extract page content in 'markdown', 'text', or 'html' format. |
| browser_get_linksC | Extract all interactive hyperlinks from the current page. |
| browser_screenshotC | Capture a screenshot of the active page and save it as PNG. |
| browser_evaluateC | Evaluate arbitrary JavaScript expression in the page context. |
| browser_tabsB | List all open tabs. |
| browser_new_tabC | Open a new browser tab with optional URL. |
| browser_switch_tabC | Switch active focus to a specific tab index. |
| browser_close_tabC | Close a specific tab or the current tab. |
| browser_waitA | Wait for seconds (e.g. '2.5') or wait for a CSS/text selector to appear. |
| browser_batchC | Execute a sequence of browser actions in a single rapid batch to eliminate round-trip overhead. |
| browser_run_codeC | Execute Python automation code directly inside the resident browser daemon. |
| browser_stopB | Gracefully stop the background browser process. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 20 tools
Most tools map to a distinct browser action (navigate, click, type, scroll, screenshot, etc.), and the descriptions differentiate the tricky pair browser_evaluate (JS in page context) vs browser_run_code (Python in the daemon). Minor overlaps remain: browser_status also reports active tabs, browser_tabs lists them, and browser_focus vs browser_launch(focus=True) can be confused with browser_batch abstracting over multiple actions.
Every tool uses the same browser_ prefix followed by a concise snake_case verb or verb_noun (browser_navigate, browser_new_tab, browser_close_tab). There are no camelCase or style deviations, making the set highly predictable.
20 tools is on the heavy side, but for a full browser automation daemon each tool covers a real capability (lifecycle, navigation, input, extraction, tab management, waiting, plus batch/JS/Python escape hatches). It is slightly over the comfortable 3-15 band but not gratuitously bloated.
Core lifecycle, navigation, interaction, extraction, screenshotting, tab management, and waiting are all covered, with evaluate/run_code/batch acting as powerful escape hatches. Gaps exist for history actions (back/forward/reload), hover/select/file-upload, and cookie/storage management, but most are workaroundable via browser_evaluate.