browser-for-claude
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": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| browser_navigateB | Navigate the headed Chromium window to a URL |
| browser_clickC | Click an element matching a CSS selector |
| browser_typeC | Fill a text input matching a CSS selector |
| browser_get_textA | Read the text content of an element matching a CSS selector |
| browser_screenshotA | Capture a PNG screenshot of the current page |
| browser_evaluateB | Evaluate a JavaScript expression in the page context and return the result |
| browser_get_urlA | Return the current page URL |
| browser_closeA | Close the Chromium window and end the session |
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 8 tools
Each tool has a clearly distinct purpose: navigating, clicking, typing, reading text, evaluating JS, taking screenshots, getting the URL, and closing the browser. There is no ambiguity or overlap.
All tools share the 'browser_' prefix and follow a consistent verb-based pattern (navigate, click, type, get_text, evaluate, get_url, close). 'browser_screenshot' is the only deviation but still reads as an action.
With 8 tools, the set is appropriately scoped for browser automation, covering session management, navigation, interaction, inspection, and evaluation. Each tool earns its place.
The set covers core browser workflows, but lacks explicit back/forward/refresh or wait commands. However, browser_evaluate can compensate for these missing operations, making gaps minor.