PhantomHand
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Capabilities
Features and capabilities supported by this server
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| get_extension_infoA | Get the absolute local path to the unpacked browser extension folder. Use this to help the user load the extension if it is not connected. |
| browser_navigateC | Navigate the active browser tab to a specific URL. |
| browser_scanA | Scan the current page viewport, returning a list of interactable elements and their physical coordinates. |
| browser_clickA | Move the mouse to physical coordinates via Bezier curve and simulate a left-click. |
| browser_typeC | Inject physical keystrokes into the active element (Requires clicking the element first). |
| browser_scrollC | Scroll the page using physical mouse wheel events. |
| browser_press_keyB | Press a special key (e.g., Enter, Tab, Escape, Backspace). |
| browser_hoverB | Hover the mouse over a specific physical coordinate. |
| browser_eval_jsB | Evaluate arbitrary JavaScript in the context of the active page. |
| browser_get_htmlB | Get the HTML content of the active page or a specific CSS selector. |
| browser_upload_fileC | Upload a local file to a file input element by CSS selector. |
| browser_extract_textB | Get the raw text content of the active page or a specific CSS selector. |
| browser_get_attributesC | Get all attributes of an element by CSS selector. |
| browser_scroll_to_elementB | Scroll the page so the specified element is centered in the viewport. |
| browser_double_clickB | Double-click at physical coordinates. Useful for selecting a word in text. |
| browser_triple_clickA | Triple-click at physical coordinates to select all text in the target element (e.g., select entire text in an input field). |
| browser_right_clickC | Right-click (context menu) at physical coordinates. |
| browser_dragA | Drag from one coordinate to another with smooth intermediate steps. Useful for drag-and-drop, slider manipulation, or text selection by dragging. |
| browser_clipboard_setC | Write text to the system clipboard. |
| browser_clipboard_getA | Read text from the system clipboard. |
| browser_select_allA | Select all text/content in the currently focused element (Ctrl+A). Commonly used before typing to replace existing text in input fields. |
| browser_keyboard_shortcutB | Send a keyboard shortcut with modifier keys. Examples: Ctrl+C for copy, Ctrl+V for paste, Ctrl+A for select all, Ctrl+Z for undo, Ctrl+Shift+I for DevTools. |
| browser_set_valueA | Directly set the value of an input or textarea element by CSS selector, bypassing the need to click and type. Triggers input and change events. Use this for fast, reliable form filling. |
| browser_clear_valueA | Clear the value of an input or textarea element by CSS selector and trigger change events. |
| browser_select_optionA | Select an option in a dropdown by value attribute or visible text. |
| browser_checkB | Check or uncheck a checkbox or radio button by CSS selector. |
| browser_focusC | Focus on an element identified by CSS selector. |
| browser_screenshotA | Take a screenshot of the current visible page and return it as an image. |
| browser_waitA | Wait/pause for a specified number of milliseconds before the next action. Useful for waiting for animations, AJAX requests, or page transitions. Default: 1000ms, Max: 30000ms. |
| browser_fast_forwardA | Instantly fast-forward virtual time (e.g., to skip countdowns or animations) without real-world waiting. |
| browser_wait_for_downloadA | Wait for a download to complete and get its path. Default timeout 30s. |
| browser_tab_newA | Open a new browser tab, optionally navigating to a URL. |
| browser_tab_closeA | Close the current active browser tab. |
| browser_tab_listA | List all open browser tabs with their IDs, titles, and URLs. |
| browser_tab_switchA | Switch to a specific browser tab by its tab ID (obtained from browser_tab_list). |
| browser_go_backA | Navigate back in the browser history. |
| browser_go_forwardA | Navigate forward in the browser history. |
| browser_reloadA | Reload the current page. |
| browser_get_page_infoA | Get the current page URL and title. |
| browser_session_exportA | Export cookies for the current domain to bypass logins later. |
| browser_session_importB | Import cookies into the current domain (JSON string). |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
Latest Blog Posts
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/SilenceEchoLab/PhantomHand'
If you have feedback or need assistance with the MCP directory API, please join our Discord server