mcp-aoai-web-browsing
If you are the rightful owner of mcp-aoai-web-browsing and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.
A minimal server/client application implementation utilizing the Model Context Protocol (MCP) and Azure OpenAI.
The Model Context Protocol (MCP) server and client implementation for Azure OpenAI is a minimalistic application designed to facilitate secure and controlled interactions between AI applications and resources. Built using FastMCP, this server leverages the capabilities of Playwright, an open-source testing framework by Microsoft, to test modern web applications. The server's response is converted to the OpenAI function calling format using a customized MCP-LLM Bridge, ensuring seamless communication between MCP servers and OpenAI-compatible LLMs. The server object is directly passed into the bridge to maintain a stable connection. This implementation is particularly useful for developers looking to integrate Azure OpenAI with MCP, providing a robust framework for building AI-driven applications.
Features
- Built with FastMCP for efficient server creation.
- Utilizes Playwright for end-to-end testing of web applications.
- Converts MCP server responses to OpenAI function calling format.
- Custom MCP-LLM Bridge for seamless communication with OpenAI LLMs.
- Direct server object integration for stable connections.