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 | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| pinchtab_list_instances | List all open browser tabs. Returns tab IDs, URLs, and titles. |
| pinchtab_close_tab | Close the current tab or a specific tab by its ID. |
| pinchtab_cookies | Get all cookies for the current page. |
| pinchtab_health | Check if PinchTab server is running and responsive. |
| pinchtab_navigate | Navigate the browser to a URL. Set waitMs to wait for page load and get a snapshot back automatically. |
| pinchtab_snapshot | Get an accessibility tree snapshot of the page. Returns element refs (e0, e1, …) that can be used with click/type/press. Use filter='interactive' for fewer tokens. Use format='compact' for minimal output. |
| pinchtab_scroll | Scroll the page or a specific element. Supports all four directions. |
| pinchtab_wait | Wait for a specified number of seconds. Useful after navigation or dynamic content loading. |
| pinchtab_wait_for_selector | Wait for a CSS selector to appear on the page. Polls every 500ms up to the timeout. Useful for waiting on dynamic content, modals, or lazy-loaded elements. |
| pinchtab_click | Click an element by its ref ID (e.g. 'e5'). Uses human-like click by default. Set waitMs to get a snapshot after clicking (saves a round-trip). For SPAs, clicking may not cause full navigation. |
| pinchtab_type | Type text into an input field by its ref ID. Uses human-like typing by default. Set clearFirst=true to click, select all, then type — required for React/Vue/Angular inputs where direct fill doesn't trigger state updates. |
| pinchtab_press | Press a keyboard key (e.g. 'Enter', 'Tab', 'Escape', 'ArrowDown'). Optionally target a specific element. |
| pinchtab_hover | Hover over an element by its ref ID. Triggers mouseover/mouseenter events — useful for revealing tooltips, dropdown menus, or hover states. |
| pinchtab_focus | Focus an element by its ref ID. Useful for triggering focus-dependent UI (e.g. autocomplete dropdowns) without clicking. |
| pinchtab_select | Select an option in a dropdown by its ref ID. Pass the option value or visible text. |
| pinchtab_get_text | Get readable text content from the page (~800 tokens). Best for extracting article content or page information. |
| pinchtab_screenshot | Take a screenshot of the page. Returns a base64-encoded image. |
| pinchtab_eval | Execute JavaScript code in the page context. Returns the result of the expression. |
| pinchtab_pdf | Export the current page as a PDF. Returns the PDF as base64. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |