MCP-AOAI-Web-Browsing

by kimtth

AI/Integration Azure OpenAI Playwright FastMCP Web Browsing Function Calling

A minimal server/client application implementation utilizing the Model Context Protocol (MCP) and Azure OpenAI. It leverages FastMCP, Playwright, and customizes the MCP-LLM Bridge for OpenAI function calling format.

View on GitHub

Last updated: N/A

What is MCP-AOAI-Web-Browsing?

This is a server and client implementation that integrates the Model Context Protocol (MCP) with Azure OpenAI for web browsing capabilities. It uses Playwright for browser automation and bridges the MCP server response to OpenAI function calling format.

How to use MCP-AOAI-Web-Browsing?

Rename .env.template to .env and fill in Azure OpenAI credentials. 2. Install uv using pip install uv and then run uv sync. 3. Execute python chatgui.py to launch the client.

Key features of MCP-AOAI-Web-Browsing

MCP integration
Azure OpenAI compatibility
Playwright web automation
OpenAI function calling
FastMCP server
Customizable MCP-LLM Bridge

Use cases of MCP-AOAI-Web-Browsing

Automated web navigation
AI-powered web scraping
Testing web applications with AI
Integrating web browsing into AI workflows

FAQ from MCP-AOAI-Web-Browsing

What is MCP?

Model Context Protocol (MCP) is an open protocol that enables secure, controlled interactions between AI applications and local or remote resources.

What is FastMCP?

FastMCP is a Pythonic way to build MCP servers.

What is Playwright?

Playwright is an open-source, end-to-end testing framework by Microsoft for testing modern web applications.

What is the MCP-LLM Bridge?

The MCP-LLM Bridge enables communication between MCP servers and OpenAI-compatible LLMs.

Why use uv for dependency management?

During the development phase in December 2024, the Python project should be initiated with 'uv'. Other dependency management libraries, such as 'pip' and 'poetry', are not yet fully supported by the MCP CLI.