AI Workflow Platform
Autonomous Agentic Automation with MCP & Playwright
An AI-powered workflow automation system exploring autonomous agents, Model Context Protocol (MCP) servers, browser automation, and containerized cloud runtimes.
The Challenge & Context
Traditional LLM agents suffer from brittle tool executions, hallucinated parameters, and lack of real-time environment feedback when executing multi-step web and cloud workflows.
Engineering Approach
Architected an agentic execution platform that utilizes Model Context Protocol (MCP) servers for standardized tool interfaces and Playwright for deterministic browser automation, running in isolated container environments.
Components & Data Flow
A Next.js frontend interacts with a FastAPI orchestrator service. The orchestrator dispatches tasks to ephemeral Docker containers in Azure Container Apps. The containers communicate via MCP to interact with external APIs, databases, and browser sessions.
Key Trade-offs & Decisions
Model Context Protocol over Custom Function Calling
MCP provides a standardized protocol for tool discovery, client-server separation, and deterministic schema validation.
Azure Container Apps with KEDA Scale-to-Zero
Workload execution is event-driven; scaling containers to zero when idle eliminates idle compute costs.
Obstacles & How They Were Overcome
RESOLUTION:Engineered aggressive container garbage collection and browser session recycling to prevent memory leaks during long-running tasks.