CloakBrowser MCP Server
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": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| cloak_launchA | Launch a stealth CloakBrowser instance. Call this before any other cloak tool. |
| cloak_closeA | Close the browser and clean up resources. |
| cloak_navigateA | Navigate to a URL and return a compact snapshot of the page. |
| cloak_snapshotC | Get a text-based snapshot of the current page's accessibility tree with ref IDs for interactive elements. |
| cloak_clickB | Click on an element identified by its ref ID from the snapshot (e.g. '@e5'). |
| cloak_typeA | Type text into an input field identified by its ref ID. |
| cloak_pressA | Press a keyboard key (Enter, Tab, Escape, ArrowDown, etc.). |
| cloak_scrollB | Scroll the page in a direction. |
| cloak_backA | Navigate back in browser history. |
| cloak_forwardB | Navigate forward in browser history. |
| cloak_consoleC | Get browser console output or evaluate JavaScript expression. |
| cloak_get_imagesA | Get a list of all images on the current page with URLs and alt text. |
| cloak_screenshotC | Take a screenshot of the current page. Returns a PNG image. |
| cloak_wait_forB | Wait for an element or text to appear on the page. |
| cloak_evaluateC | Evaluate JavaScript expression in the page context. |
| cloak_get_contentB | Get text or HTML content of an element or the entire page. |
| cloak_extract_linksA | Extract all links from the current page as JSON. |
| cloak_fill_formC | Fill multiple form fields at once. |
| cloak_hoverB | Hover over an element identified by its ref ID. |
| cloak_select_optionC | Select option(s) in a element. |
| cloak_dragB | Drag an element from one position to another. |
| cloak_save_storage_stateB | Save browser storage state (cookies, localStorage) to a JSON file. |
| cloak_load_storage_stateA | Load browser storage state from a JSON file. |
| cloak_infoA | Get information about the current browser session (URL, title, viewport). |
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 24 tools
Each tool targets a distinct action: navigation, interaction, state management, information retrieval, or waiting. No two tools have overlapping purposes; even similar ones like cloak_console and cloak_evaluate are differentiated by scope (console output vs. arbitrary JS evaluation).
All tools follow a consistent 'cloak_verb' pattern in snake_case, with descriptive and predictable verb choices (e.g., cloak_navigate, cloak_click, cloak_snapshot). No deviations or mixed styles.
24 tools is on the higher end but each serves a clear and necessary function in browser automation. The count is justified by the breadth of tasks (navigation, DOM interaction, state management, etc.) and does not feel excessive.
The tool surface covers all core browser automation workflows: navigation, element interaction, form handling, state persistence, and information extraction. Minor gaps exist (e.g., no explicit tab management or dialog handling), but they do not critically impair common use cases.