Azure OpenAI MCP
A minimal server/client application implementation utilizing the Model Context Protocol (MCP) and Azure OpenAI.
What is Azure OpenAI MCP?
Azure OpenAI MCP is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to minimal server/client application implementation utilizing the model context protocol (mcp) and azure openai.
A minimal server/client application implementation utilizing the Model Context Protocol (MCP) and Azure OpenAI.
This server falls under the Cloud Services and Browser Automation categories on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- A minimal server/client application implementation utilizing
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx azure-openaiConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Azure OpenAI MCP
This project implements a minimal but functional MCP server and client bridge that wires Azure OpenAI (or standard OpenAI) to Playwright-based web browsing capabilities. The server exposes a playwright_navigate tool that an LLM can invoke to control a real browser, enabling AI-driven web automation workflows such as scraping, form filling, and multi-step web interactions. It is a practical reference implementation for teams building agentic AI systems on Azure infrastructure that need browser control alongside language model reasoning.
Prerequisites
- Python 3.10 or later
- uv package manager installed (pip install uv or brew install uv)
- An Azure OpenAI resource with a deployed GPT model, or an OpenAI API key
- Playwright browsers installed (playwright install)
- An MCP client such as Claude Desktop, or run the included chatgui.py client directly
Clone the repository
Download the source code.
git clone https://github.com/kimtth/mcp-aoai-web-browsing.git && cd mcp-aoai-web-browsingInstall Python dependencies with uv
uv resolves and installs all packages declared in the project lockfile.
pip install uv && uv syncInstall Playwright browser binaries
Download the Chromium (and optionally Firefox/WebKit) browser binaries that Playwright will control.
uv run playwright installConfigure environment variables
Create a .env file in the project root with your Azure OpenAI or OpenAI credentials.
AZURE_OPEN_AI_ENDPOINT=https://YOUR_RESOURCE.openai.azure.com/
AZURE_OPEN_AI_API_KEY=YOUR_API_KEY
AZURE_OPEN_AI_DEPLOYMENT_MODEL=gpt-4o
AZURE_OPEN_AI_API_VERSION=2024-02-01Run the chat GUI to test the setup
Launch the built-in Gradio chat interface. This starts the MCP server in-process and lets you send browser automation commands.
uv run python chatgui.pyOptional: configure as an MCP server in Claude Desktop
To use this as a standalone MCP server for Claude Desktop, add the configuration below to claude_desktop_config.json.
Azure OpenAI MCP Examples
Client configuration
Add to claude_desktop_config.json to expose the Playwright browser tool to Claude Desktop. The server runs via uv and fastmcp.
{
"mcpServers": {
"aoai-web-browsing": {
"command": "uv",
"args": ["run", "fastmcp", "run", "./server/browser_navigator_server.py:app"],
"env": {
"AZURE_OPEN_AI_ENDPOINT": "https://YOUR_RESOURCE.openai.azure.com/",
"AZURE_OPEN_AI_API_KEY": "YOUR_API_KEY",
"AZURE_OPEN_AI_DEPLOYMENT_MODEL": "gpt-4o",
"AZURE_OPEN_AI_API_VERSION": "2024-02-01"
}
}
}
}Prompts to try
Commands that drive the Playwright browser tool through the MCP interface.
- "Navigate to https://news.ycombinator.com and summarise the top 5 headlines"
- "Go to https://example.com, take a screenshot, and describe what you see"
- "Open https://en.wikipedia.org/wiki/Model_Context_Protocol and extract the introduction section"
- "Browse to a product page on a public e-commerce site and list the key specifications"Troubleshooting Azure OpenAI MCP
playwright install fails or browsers do not launch
Run 'uv run playwright install --with-deps' to also install OS-level dependencies. On Linux you may also need 'apt-get install -y libgbm1 libasound2'.
Azure OpenAI returns 401 or 404 errors
Double-check AZURE_OPEN_AI_ENDPOINT (must include trailing slash and correct resource name), AZURE_OPEN_AI_DEPLOYMENT_MODEL (must match the exact deployment name in Azure Portal), and AZURE_OPEN_AI_API_VERSION.
uv sync fails with 'no project found'
Run the command from the repository root where pyproject.toml lives. Do not cd into a subdirectory before running uv sync.
Frequently Asked Questions about Azure OpenAI MCP
What is Azure OpenAI MCP?
Azure OpenAI MCP is a Model Context Protocol (MCP) server that minimal server/client application implementation utilizing the model context protocol (mcp) and azure openai. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Azure OpenAI MCP?
Follow the installation instructions on the Azure OpenAI MCP GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Azure OpenAI MCP?
Azure OpenAI MCP works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Azure OpenAI MCP free to use?
Yes, Azure OpenAI MCP is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.
Azure OpenAI MCP Alternatives — Similar Cloud Services Servers
Looking for alternatives to Azure OpenAI MCP? Here are other popular cloud services servers you can use with Claude, Cursor, and VS Code.
Open WebUI
★ 138.2kUser-friendly AI Interface (Supports Ollama, OpenAI API, ...)
Anything LLM
★ 60.4kThe all-in-one AI productivity accelerator. On device and privacy first with no annoying setup or configuration.
LocalAI
★ 46.4kLocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.
Nacos
★ 33.0kan easy-to-use dynamic service discovery, configuration and service management platform for building AI cloud native applications.
Xiaozhi ESP32
★ 26.7k本项目为xiaozhi-esp32提供后端服务，帮助您快速搭建ESP32设备控制服务器。Backend service for xiaozhi-esp32, helps you quickly build an ESP32 device control server.
Gateway
★ 11.8kA blazing fast AI Gateway with integrated guardrails. Route to 1,600+ LLMs, 50+ AI Guardrails with 1 fast & friendly API.
Browse More Cloud Services MCP Servers
Explore all cloud services servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Azure OpenAI MCP in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Azure OpenAI MCP?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.