stealth-browser-mcp
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_navigateA | Navigate the stealth browser to a target URL with persistent authentication. |
| browser_autofill_loginA | Automatically fill and submit a login form using credentials stored securely in macOS Keychain. |
| passkey_enable_virtual_authenticatorC | Enables a Chrome DevTools Protocol (CDP) WebAuthn virtual authenticator and optionally injects a stored Passkey credential from Keychain. |
| passkey_save_registrationB | Captures newly registered Passkey credentials from the virtual authenticator and saves them to macOS Keychain for future automated logins. |
| keychain_store_credentialA | Store a username and password securely in macOS Keychain so the browser agent can log in automatically later. |
| browser_clickA | Click an element on the page using human-like mouse movement and click delays. |
| browser_typeB | Type text into an input or textarea with realistic human keystroke timing delays. |
| browser_screenshotA | Capture a screenshot of the current page for visual inspection. |
| browser_extract_textA | Extract cleaned text, links, and forms from the page for LLM reading. |
| browser_extract_htmlC | Extract outer HTML of a specific element or the entire page DOM. |
| browser_evaluateB | Execute a custom JavaScript expression in the active page context and return the result. |
| browser_scrollB | Scroll the viewport up or down. |
| browser_wait_forB | Wait for a CSS selector to appear or sleep for a specified duration in milliseconds. |
| browser_open_interactive_windowA | Opens a non-headless visible Chrome window on the user desktop so the user can manually solve a CAPTCHA or complete 2FA. |
| browser_statusB | Check the current status of the browser instance, active tabs, and persistent profile path. |
| browser_closeA | Gracefully close the browser and flush session cookies/storage to disk. |
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 16 tools
Each tool has a clearly distinct purpose: navigation, login, passkey management, keychain storage, clicking, typing, screenshotting, text extraction, HTML extraction, JS evaluation, scrolling, waiting, interactive window, status, and close. The overlap between extract_text and extract_html is minor and well-explained by their descriptions.
Tool names follow a consistent pattern with functional prefixes (browser_, passkey_, keychain_) and descriptive verb_noun or verb_object combinations. All verbs are clear and consistently styled (snake_case), making the set predictable and scannable.
16 tools is appropriate for a browser automation server covering navigation, interaction, authentication, extraction, and lifecycle management. Each tool earns its place and the count is neither sparse nor bloated for the intended scope.
The tool surface covers core browser automation workflows: navigation, login, passkey handling, interaction, content extraction, and browser lifecycle. Minor gaps exist such as explicit back/forward navigation or download handling, but these do not critically hinder typical automation tasks.