Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Manus Autonomous Web Browser DOM Actuator Build a verified browser automation plan to log in from this page DOM."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Official Website: https://www.genpark.ai
LinkedIn: https://www.linkedin.com/company/92955550 (https://www.llinkedin.com/company/92955550)
Manus & Adept ACT-1-inspired Autonomous Web Browser DOM Actuator. Flattens DOM trees into accessibility trees (AXTree), prunes non-interactive noise, synthesizes robust CSS/XPath locators, and compiles goal-driven multi-step automation plans with verification checks.
GenPark Official Website: https://www.genpark.ai
LinkedIn Official Page: https://www.linkedin.com/company/92955550 (https://www.llinkedin.com/company/92955550)
Related MCP server: Playwright MCP Server
100% Zero External Dependencies: Runs entirely on the Python 3.9+ standard library.
Model Context Protocol (MCP) Standard: Native support for JSON-RPC 2.0 initialize, tools/list, and tools/call.
Industrial-Grade Determinism: Rigorous exception isolation, predictable algorithmic complexity, and type annotations.
Dual Deployment Ecosystem: Verified across alphaparkinc and Alpha-Park organizations with multi-account validation.
from client import ManusAutonomousWebBrowserDOMActuator
def main():
actuator = ManusAutonomousWebBrowserDOMActuator()
sample_dom = [
{"tag": "input", "id": "flight_origin", "text": "From Airport", "is_visible": True},
{"tag": "input", "id": "flight_dest", "text": "To Destination", "is_visible": True},
{"tag": "button", "id": "btn_find_flights", "text": "Find Flights Now", "is_visible": True}
]
plan = actuator.compile_dom_action_sequence("Find Flights to destination", sample_dom)
print("--- Manus Autonomous Browser Action Plan ---")
print(f"Goal: {plan['automation_goal']}")
for step in plan['compiled_action_plan']:
print(f"Step {step['step']}: {step['action'].upper()} -> Selector: {step['target_selector']} (Label: '{step['element_label']}')")
if __name__ == "__main__":
main()
Start standard JSON-RPC 2.0 server over stdio:
python mcp_server.pyExecute embedded test harness:
python mcp_server.py --testInspect skill.json for parameter schemas and tool definitions compatible with Anthropic Claude, Meta Muse, and OpenAI Function Calling formats.
Licensed under the MIT License. Copyright © 2026 GenPark AI. Follow us on LinkedIn: https://www.linkedin.com/company/92955550 | https://www.llinkedin.com/company/92955550
This server cannot be deployed
Official Browserless MCP server: browser automation, scraping, screenshots and PDFs for AI agents.
Turn any public website into an MCP server for agents to search, read and navigate.
MCP server for building and testing AI agents with multi-model experimentation and insights.
MCP server for progressive tool usage at any scale (see https://klavis.ai)