ghostfox
Related Servers
Alternatives to ghostfox
- AlicenseAqualityDmaintenanceEnables cloud browser automation through Browserbase and Stagehand, allowing LLMs to interact with web pages, take screenshots, extract data, and perform automated actions with support for proxies, stealth mode, and parallel sessions.142,401 npmApache 2.0
Related Servers
- AlicenseAqualityAmaintenanceA stealth Firefox browser exposed as an MCP server that lets AI agents browse and interact with real websites without being blocked by anti-bot systems.184MIT
- AlicenseNot gradedqualityDmaintenanceEnables AI agents to drive a privacy-first browser via MCP, using diff-based page observation to reduce token consumption, and offering secure autofill from a local vault.4,922 npmMIT
- AlicenseCqualityAmaintenanceNative webview browser automation for AI agents. Rust-powered, with JSON-lines control and a built-in MCP server. Runs on macOS, Linux, and Windows.43MIT
- AlicenseNot gradedqualityAmaintenanceExposes a 47-tool browser automation surface to MCP clients, enabling AI agents to navigate, interact with, observe, and extract content from web pages across multi-tab sessions. Runs on Camoufox-based anti-detection behavior so agents can automate sites that block conventional headless browsers, with session persistence, cookie import, and stdio or HTTP transport.971 npmMIT
- AlicenseNot gradedqualityDmaintenanceA local MCP server for Firefox that gives AI agents full control over the browser via a Unix socket, enabling automation of tabs, pages, cookies, and more without exposing any network ports.36 npmMIT
- AlicenseBqualityBmaintenanceEnables AI agents to drive a Camoufox (Firefox-based) browser over MCP stdio or HTTP/REST, with persistent profiles, structured extraction, file upload/download, secret-filled logins, reusable scheduled flows, and a human-in-the-loop live view.26MIT
TDQS
Scored across 42 tools
Some overlap exists among the many vision, input, and captcha tools (e.g., page_snapshot vs page_a11y vs page_ocr, or page_type vs page_type_ref vs page_fill), though the descriptions do a good job of explaining when to prefer one over another. The highly specialized captcha solvers are each tied to a specific challenge type, but the sheer number of adjacent tools still creates selection ambiguity.
The vast majority of tools follow a clear page_<verb_or_noun> snake_case convention, with session_ and identity_ prefixes for lifecycle and identity concerns. Minor deviations like captcha_solve, confirm_action, and the noun-style page_console/page_a11y keep it from being perfectly uniform, but the overall pattern is predictable.
At 42 tools, this is well above the 25+ threshold and feels too heavy even for a broad stealth-browser and captcha-solving purpose. Many vision and captcha variants could likely be consolidated or surfaced through a smaller capability-oriented set. The count is not chaotic enough for a 1, but it will tax an agent's ability to choose efficiently.
The toolset covers the core lifecycle thoroughly: session creation, identity generation/audit, page navigation, interaction, reading, network capture, console/error introspection, captcha solving, and evidence retrieval. Minor gaps like explicit session teardown, page reload/back-forward navigation, or cookie management are missing, but agents can work around those with page_eval and navigation to a URL.