Skip to main content
Glama
mienetic

Ghostvault

by mienetic

Open Anonymous Browser Session

gv_open_ephemeral

Launch a temporary, anonymous browser session for scraping public pages. No login required; session data self-destructs after use.

Instructions

Open a throwaway browser session for anonymous scraping — NO account needed.

Launches a fresh Camoufox browser with a random identity, no persistent profile, and no DB row. Nothing survives the session — perfect for public pages that don't require login.

The session becomes the active target, so ALL existing browser tools work on it unchanged: gv_open_url, gv_get_page_content, gv_screenshot, gv_get_page_links, gv_click_element, gv_fill_input, gv_scroll, gv_press_key.

Defaults are tuned for scraping: headless=True, block_images=True, short 5-minute idle auto-close. Override per call if needed.

Args: url: Optional URL to navigate to immediately. Omit to start on a blank page. headless: Override the default (True). Set False to watch the browser. proxy: Optional Playwright-style proxy dict (same format as gv_create_account). block_images: Override the default (True). Set False if you need screenshots.

Returns the session id + next steps.

When done, call gv_close_ephemeral. The session also auto-closes after GHOSTVAULT_EPHEMERAL_AUTO_CLOSE_MINUTES idle (default 5).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
urlNo
proxyNo
headlessNo
block_imagesNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Discloses no persistent profile, no DB row, session being active target, default headless/block_images, 5-min auto-close. Contradicts no annotations (openWorldHint is consistent).

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Well-structured with clear opening, parameter bullets, default guidance, and lifecycle notes. Every sentence adds value without redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Covers all aspects: purpose, use case, parameters, defaults, return value, lifecycle, and integration with sibling tools. Nothing missing for an AI agent.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Despite 0% schema coverage, description explains each parameter's purpose and defaults, adding significant meaning beyond schema types.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Clearly states 'Open a throwaway browser session for anonymous scraping' with specific verb and resource. Distinguishes from siblings like gv_open_account by emphasizing no login needed.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly says 'NO account needed', 'perfect for public pages', and provides lifecycle guidance (call gv_close_ephemeral). Defaults and overrides are clearly stated.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

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/mienetic/Ghostvault'

If you have feedback or need assistance with the MCP directory API, please join our Discord server