AginxBrowser
Related Servers
Alternatives to AginxBrowser
No user-submitted related servers found.
Related Servers
- AlicenseNot gradedqualityAmaintenanceEnables an AI agent to observe, plan, and act inside a real browser session by exposing navigation, snapshot, click, type, and screenshot MCP tools over local JSON-RPC and SSE. It runs a Playwright-backed browser in-process and provides stable element references for reliable actions.MIT
- AlicenseAqualityCmaintenanceBrowser automation MCP server that uses a real browser to give agents eyes and hands—open pages, click, fill, screenshot, and run scripts via accessibility-tree snapshots.226 npmMIT
- AlicenseNot gradedqualityBmaintenanceText-first browser automation MCP server: reads pages via the accessibility tree (~500 tokens/page), CDP engine with 27 tools, network-layer scraping (JSON API bodies), cookie vault + auto session restore, and a ~0.02s unix-socket daemon for agents.MIT
- AlicenseBqualityBmaintenanceA local MCP server that lets agents drive browser sessions across a stealth Chromium engine, stock Chromium for devtools, and a lightweight Rust engine, acting on stable element refs and receiving compact snapshots plus only-what-changed diffs after each action. It adds per-origin workflow memory, SSRF and origin guards, risk-gated high-impact clicks, and a reproducible benchmark harness.35MIT
- AlicenseNot gradedqualityNot gradedmaintenanceA Playwright-based MCP server that exposes a live browser as a traceable, inspectable, debuggable and controllable execution environment for AI agents.5,213 npm57-
- AlicenseNot gradedqualityAmaintenanceEnables AI agents to run Playwright-compatible browser automation with persistent profiles, proxies, Chrome extensions, and humanized mouse, keyboard, and scroll interactions over stdio or Streamable HTTP. Supports web research, daily automation, testing workflows, and optional session-scoped CDP access.280 npmMIT
TDQS
Scored across 40 tools
Tool families are cleanly separated: stateless fetch/eval/click are explicitly distinguished from their session_* counterparts, and account_*/render_*/session_* names signal intent. The main fuzzy boundaries are session_challenges vs session_verdict (both report anti-bot/risk status) and the three render_* tools, though descriptions usually resolve them.
Most tools follow predictable families—account_<verb>, session_<operation>, render_<format>—and bare stateless verbs (fetch, search, eval, click) are easy to read. Deviations such as flow_run instead of run_flow and noun-style read tools like session_state/session_network/session_cookies keep it from being perfectly uniform.
40 tools is a heavy surface, especially with 26 session_* variants; even though each is a real browser action, the set will tax an agent's selection and context budget. The server's broad scope explains the count, but it still exceeds what most MCP clients handle gracefully.
The surface covers the full browser workflow: read/search/download, session lifecycle and input, login-state persistence, risk-control verdicts, flow replay, and render/export targets. Minor gaps such as no explicit multi-tab/window management or standalone proxy/user-agent configuration are workaroundable.