superpowers-chrome
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| DISPLAY | No | For Linux/WSL2 headed mode, set DISPLAY environment variable (e.g., ':0') | |
| CHROME_WS_HOST | No | Override host for DevTools traffic (default 127.0.0.1) | |
| CHROME_WS_PORT | No | Override port for Chrome DevTools (default dynamically allocated from range 9222-12111) | |
| CHROME_EXTRA_ARGS | No | Whitespace-separated list of additional Chrome flags (e.g., '--use-gl=angle --use-angle=swiftshader-webgl') | |
| CHROME_WS_PROFILE | No | Set a fixed profile name to share Chrome between processes |
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": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| use_browserA | Control persistent Chrome browser with automatic page capture. Every DOM action (navigate, click, type, select, eval) auto-captures to the session dir:
Prefer reading these files to using 'extract' or 'screenshot' whenever possible. Pages showing credential-shaped content (tokens, 2FA seeds) are never captured, and such values are redacted from all output. Schema: 4 parameters — action, selector (CSS/XPath or null), payload (string or object), timeout (ms). selector targets a DOM element (null/omit for navigation, eval, tab management, etc.). payload is a string for simple actions (navigate=URL, type=text, eval=JS, keyboard_press=key). payload is an object for structured actions (set_viewport={width,height}, drag_drop={target}, etc.) — a JSON-encoded string of the same object works too. Tabs are tracked as sticky state; use switch_tab to change the active tab. Use action='help' for full per-action payload shapes. |
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 1 tool
There is only one tool, so there is no risk of selecting the wrong tool. The action parameter internally routes behavior, but tool-level disambiguation is trivially perfect.
The single tool name 'use_browser' follows a clear verb_noun snake_case pattern. With only one name, there is no inconsistency to evaluate.
A single tool is borderline thin for the broad browser-automation domain, even though it multiplexes many actions via the action parameter. It avoids tool sprawl but may be under-split for discoverability.
The tool covers navigation, interaction, evaluation, tab management, viewport, drag/drop, and keyboard input, plus automatic capture and redaction. A few niche browser operations may still be missing, but core lifecycle coverage is strong.