Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| DEBUG | No | Enable debug logging | false |
| NODE_ENV | No | Environment mode | development |
Schema
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| reverse_engineer_chat | Automatically reverse engineer a chat interface by navigating to the URL, sending a test message, and capturing all network traffic to identify streaming API endpoints. Returns discovered endpoints with their request/response patterns including Server-Sent Events (SSE), WebSocket connections, and chunked HTTP responses. Perfect for quick analysis of public chat interfaces without authentication. |
| initialize_session | Create a persistent browser session for step-by-step reverse engineering of complex chat interfaces. Use this when the chat requires login, multi-step navigation, or manual interaction before analysis. Returns a sessionId that must be used with all subsequent interactive tools. The session maintains cookies, authentication state, and can be used across multiple operations until explicitly closed. |
| take_screenshot | Capture a screenshot of the current browser page as a base64-encoded PNG image. Essential for visual feedback to understand what's displayed before deciding which buttons to click or forms to fill. Supports capturing the visible viewport, entire scrollable page, or specific elements. Returns the image as base64 string and data URL for easy display. |
| click_element | Click a button, link, or any interactive element on the page. Useful for navigating through multi-step interfaces, opening chat modals, starting new conversations, or triggering UI actions. Can target elements by CSS selector or by their visible text content. Automatically waits after clicking to allow page updates. |
| fill_form | Fill out one or multiple form fields in sequence, perfect for login forms, registration, search inputs, or any text entry. Supports pressing Enter after each field and clicking a submit button. Commonly used for authentication flows before accessing chat interfaces. Each field can be filled independently with optional Enter key press. |
| switch_tab | Switch the active browser tab when multiple tabs are open in the session. Common scenario: clicking a link that opens a chat in a new tab requires switching to that tab to interact with it. Use get_current_page_info first to see all available tabs and their indices. |
| navigate_to_url | Navigate to a different URL within the same browser session. Maintains all cookies, authentication state, and session data. Useful for moving between different sections of a website (e.g., from login page to chat page, or from homepage to a specific conversation URL). Supports different wait strategies for page load completion. |
| wait_for_element | Wait for a specific element to appear on the page before continuing. Essential for handling dynamic content that loads asynchronously, page transitions, or elements that appear after clicking buttons. Prevents errors from trying to interact with elements that haven't loaded yet. Commonly used after login, navigation, or clicking buttons that trigger loading states. |
| get_current_page_info | Retrieve comprehensive information about the current browser state including current URL, page title, number of open tabs, and details about each tab. Essential for understanding where you are in a multi-step process, confirming navigation worked, or deciding which tab to switch to. Returns list of all tabs with their URLs, titles, and which one is currently active. |
| close_session | Close the browser session and free all associated resources including browser instance, pages, and contexts. Always call this when finished with a session to prevent memory leaks. The sessionId becomes invalid after closing and cannot be reused. Any unsaved work or open pages will be lost. |
| start_network_capture | Start capturing network traffic on the current browser session. Monitors all HTTP requests and responses, WebSocket frames, and streaming data. Can filter by POST requests only, streaming responses only, or specific URL patterns. Essential for analyzing API calls, debugging network issues, or monitoring real-time data flows. |
| stop_network_capture | Stop the active network capture session and return all captured data. Returns comprehensive network traffic including requests, responses, WebSocket frames, and streaming data with timestamps and headers. Use this to analyze captured network activity or save data for later processing. |
| get_network_capture_status | Get the current status of network capture for a session. Returns whether capture is active, duration, current statistics, and capture options. Useful for monitoring capture progress or checking if capture is running before stopping. |
| clear_network_capture | Clear all captured network data without stopping the capture session. Resets request/response buffers while keeping capture active. Useful for long-running captures where you want to periodically clear old data to prevent memory issues. |