nodriver-mcp-server
Related Servers
Alternatives to nodriver-mcp-server
No user-submitted related servers found.
Related Servers
- -licenseNot gradedqualityNot gradedmaintenanceUndetectable browser automation server for MCP-compatible AI agents, offering 225 tools across 32 sections to navigate, extract, clone pages, and bypass antibot systems like Cloudflare.1-
- AlicenseNot gradedqualityAmaintenanceEnables AI agents to automate the web through an anti-detection browser backend, with 47 tools for navigation, interaction, observation, search, extraction, downloads, and session reuse. Supports multi-tab workflows, persistent profiles, cookie import, and HTTP or stdio transports for MCP-compatible clients.971 npmMIT
- AlicenseNot gradedqualityDmaintenanceA stealth-enhanced browser automation MCP server for AI agents to interact with websites while bypassing anti-bot detection mechanisms like Cloudflare and reCAPTCHA.9MIT
- AlicenseNot gradedqualityAmaintenanceEnables MCP-compatible AI agents to drive an anti-detection browser for navigation, interaction, search, extraction, downloads, and persistent multi-tab sessions across 47 tools. Connects over stdio or HTTP to a separately running browser server, letting agents automate the web without getting blocked.971 npmMIT
- AlicenseNot gradedqualityDmaintenanceAn MCP server that provides AI assistants with full control over a real browser session via a Chrome extension, supporting 36 tools for navigation, data extraction, and DOM manipulation. It bypasses bot detection by utilizing the user's active browser session, including cookies, authentication tokens, and installed extensions.19 npm4MIT
- AlicenseNot gradedqualityAmaintenanceA local MCP server that lets AI coding tools drive the user's real, already-logged-in Chrome — reading pages, clicking, typing, uploading files, taking screenshots, and inspecting tabs, cookies, console, and network traffic — via 25 browser automation tools that pass bot detection without a debugging port. Requires a companion Chrome extension and stays entirely on the user's machine.1 npmISC
TDQS
Scored across 70 tools
Most tools map to a distinct resource+action, and the descriptions explicitly separate the confusable pairs (click vs click_at, fill vs type_text, emulate vs emulate_device, close_browser vs shutdown_browser, save_session vs use_profile). A few boundaries stay genuinely close — the emulate/reset_emulation/resize_page family, click vs click_at, and fill/type_text/fill_form — so an agent could still misselect occasionally, but the set is largely clean.
Names are uniformly snake_case and predominantly verb_noun (list_pages, select_page, get_cookies, set_cookie, take_snapshot), which is highly predictable. Minor deviations exist — noun-first forms (performance_start_trace, cf_verify) and bare verbs (click, hover, drag, fill) — but they are readable and not confusing.
70 tools is far beyond a comfortable surface and well past the 25+ threshold that signals heaviness. Each tool covers a genuinely distinct capability (browser/profile mgmt, navigation, interaction, storage, network, console, perf, memory, security), so it is not redundant, but the sheer breadth imposes a large selection cost on the agent.
Coverage is near-total across the automation lifecycle: profiles, sessions, tabs, navigation, interaction, cookies/storage, network capture, HAR export, console, emulation, tracing, memory snapshots and a security audit all have dedicated tools. Only minor gaps remain — no request interception/modification or mocking, no direct sessionStorage write or per-cookie delete, and IndexedDB/Cache reads are delegated to evaluate_script — all workable around.