BrowserMCP Extended
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 | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| browser_clickC | Perform click on a web page |
| browser_clipboard_writeC | Write text to the browser clipboard |
| browser_close_tabC | Close a browser tab by its tab ID |
| browser_delete_cookieC | Delete a specific browser cookie by name |
| browser_dialog_handleB | Handle a JavaScript dialog (alert, confirm, or prompt) by accepting or dismissing it |
| browser_dragB | Perform drag and drop between two elements |
| browser_drag_dropC | Perform a drag-and-drop operation between two elements identified by CSS selectors |
| browser_execute_in_frameB | Execute JavaScript code inside a specific iframe |
| execute_scriptC | Execute arbitrary JavaScript code in the active browser tab and return the result |
| browser_get_console_logsB | Get the console logs from the browser |
| browser_get_cookiesC | Get all cookies for a specific URL |
| browser_get_htmlB | Get the HTML content of the page or a specific element |
| browser_get_storageB | Read localStorage and/or sessionStorage of the active tab |
| browser_get_textC | Get the plain text content of the page or a specific element |
| browser_go_backB | Go back to the previous page |
| browser_go_forwardB | Go forward to the next page |
| browser_hoverC | Hover over element on page |
| browser_list_tabsA | List all open browser tabs with their IDs, URLs, and titles |
| browser_navigateC | Navigate to a URL |
| browser_network_clearA | Clear the captured network buffer without stopping an active capture. |
| browser_network_detailA | Read a captured request including headers, query URL, POST data, response body, timing, errors and WebSocket frames. Bodies can be unavailable or truncated; see bodyError and truncated fields. |
| browser_network_export_harA | Export captured traffic as HAR 1.2. Returns HAR JSON, or writes a new file on the MCP server machine if filePath is supplied. Existing files are not overwritten. Timing phases are aggregated; unavailable fields use HAR sentinel values. |
| browser_network_listA | List captured requests with IDs, URLs, methods, statuses, durations and failures. Supports filters and pagination. Use the returned id in browser_network_detail. |
| browser_network_startA | Start network capture on a tab. Captures future HTTP requests, responses, failures and WebSocket messages. Reload the page afterwards to capture initial loading. Starting an already active capture preserves it; starting a stopped capture resets its buffer. |
| browser_network_stopA | Stop capture and release the debugger. Recorded requests and captured bodies remain available until clear, restart or extension reload. |
| browser_new_tabB | Open a new browser tab, optionally navigating to a URL |
| browser_press_keyC | Press a key on the keyboard |
| browser_reloadA | Reload the current browser page, optionally with a hard refresh (cache bypass) |
| browser_screenshotB | Take a screenshot of the current page |
| browser_screenshot_elementB | Take a screenshot of a specific DOM element identified by a CSS selector |
| browser_screenshot_fullpageB | Capture a full-page screenshot (beyond the visible viewport) |
| browser_scrollC | Scroll the page or a specific element to given coordinates or into view |
| browser_select_optionC | Select an option in a dropdown |
| browser_set_cookieC | Set or update a browser cookie |
| browser_snapshotA | Capture accessibility snapshot of the current page. Use this for getting references to elements to interact with. |
| browser_switch_tabC | Switch to a specific browser tab by its tab ID |
| browser_typeC | Type text into editable element |
| browser_upload_fileC | Upload a file to a file input element on the page |
| browser_waitC | Wait for a specified time in seconds |
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 39 tools
Most tools target a distinct resource+action, but browser_drag and browser_drag_drop appear to be near-duplicates with only a CSS-selector phrasing difference, forcing an arbitrary choice. Content-retrieval tools (browser_get_text, browser_get_html, browser_snapshot, browser_screenshot_element) also overlap somewhat, though descriptions provide workable guidance.
The browser_ prefix is applied almost everywhere, but conventions mix: verb-first names (browser_click, browser_type, browser_get_text) sit alongside resource-then-verb names (browser_network_list, browser_network_detail, browser_screenshot_element). execute_script breaks the prefix entirely, and browser_drag vs browser_drag_drop is an inconsistent naming of essentially the same operation.
At 39 tools the surface is heavy for a browser-automation server, and several clusters could be consolidated: three screenshot variants, six network-capture tools, and two drag implementations. Individually justifiable, but as a set it exceeds a comfortably scannable scope.
Coverage is broad: navigation, tabs, interaction, cookies, storage, console logs, dialogs, iframes, uploads, screenshots, and full network capture with HAR export. Minor gaps remain (no viewport/device emulation, no read-clipboard, no selector-based wait, no storage writes), but agents can work around them.