AOAI Web Browsing MCP
A minimal Model Context Protocol 🖥️ server/client🧑💻with OpenAI and 🌐 web browser control via Playwright.
What is AOAI Web Browsing MCP?
AOAI Web Browsing MCP is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to minimal model context protocol 🖥️ server/client🧑💻with openai and 🌐 web browser control via playwright.
A minimal Model Context Protocol 🖥️ server/client🧑💻with OpenAI and 🌐 web browser control via Playwright.
This server falls under the Browser Automation and Cloud Services categories on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- A minimal Model Context Protocol 🖥️ server/client🧑💻with Ope
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx mcp-aoai-web-browsingConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use AOAI Web Browsing MCP
The AOAI Web Browsing MCP server connects AI assistants to real web browsers through Playwright automation, enabling programmatic navigation, interaction, and content extraction from any website. It bridges Azure OpenAI or standard OpenAI models with browser control so agents can perform web searches, fill forms, and scrape live pages rather than relying on static training data. Developers use it to build autonomous web agents that can research, test, and interact with web applications on demand.
Prerequisites
- Python 3.10+ and pip installed
- uv package manager installed (pip install uv)
- Azure OpenAI account with a deployed model, OR a standard OpenAI API key
- Playwright browser drivers (installed via uv sync)
- An MCP client such as Claude Desktop or VS Code with MCP extension
Clone the repository
Clone the mcp-aoai-web-browsing repository from GitHub and navigate into the project directory.
git clone https://github.com/kimtth/mcp-aoai-web-browsing.git
cd mcp-aoai-web-browsingInstall dependencies with uv
Use uv to create a virtual environment and install all required packages including Playwright and the MCP SDK.
pip install uv
uv syncConfigure environment variables
Copy the provided template to a .env file and fill in your Azure OpenAI or OpenAI credentials. For Azure OpenAI set AZURE_OPEN_AI_ENDPOINT, AZURE_OPEN_AI_API_KEY, AZURE_OPEN_AI_DEPLOYMENT_MODEL, and AZURE_OPEN_AI_API_VERSION. For standard OpenAI set OPENAI_API_KEY and OPENAI_MODEL.
cp .env.template .env
# Edit .env and set your credentialsInstall Playwright browser binaries
After the Python packages are installed, download the Playwright browser binaries required for web automation.
uv run playwright installConfigure your MCP client
Add the server to your MCP client configuration file (e.g., mcp.json or claude_desktop_config.json). The server is launched via uv run fastmcp against the browser navigator server module.
{
"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"
}
}
}
}Test the server
Verify the setup by running the chat GUI bundled with the project, which lets you interact with the browser agent directly.
uv run python chatgui.pyAOAI Web Browsing MCP Examples
Client configuration
Add this block to your claude_desktop_config.json to connect Claude Desktop to the AOAI Web Browsing server. Adjust env vars to match your Azure OpenAI deployment.
{
"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
Once connected, use these prompts to exercise the browser automation capabilities via the playwright_navigate tool and related actions.
- "Navigate to https://news.ycombinator.com and summarize the top 5 stories"
- "Go to https://example.com, take a screenshot, and describe what you see"
- "Navigate to https://httpbin.org/get and show me the response JSON"Troubleshooting AOAI Web Browsing MCP
Playwright browser not found or launch error
Run 'uv run playwright install' to download the required browser binaries. If using a virtual environment directly, also run 'playwright install' inside it.
Azure OpenAI authentication error (401 or 403)
Double-check that AZURE_OPEN_AI_ENDPOINT includes the trailing slash, AZURE_OPEN_AI_API_KEY is the key (not the endpoint), and AZURE_OPEN_AI_DEPLOYMENT_MODEL matches the exact deployment name in your Azure portal.
uv command not found after pip install uv
Ensure the pip installation target (usually ~/.local/bin) is on your PATH. Run 'export PATH="$HOME/.local/bin:$PATH"' or restart your terminal session.
Frequently Asked Questions about AOAI Web Browsing MCP
What is AOAI Web Browsing MCP?
AOAI Web Browsing MCP is a Model Context Protocol (MCP) server that minimal model context protocol 🖥️ server/client🧑💻with openai and 🌐 web browser control via playwright. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install AOAI Web Browsing MCP?
Follow the installation instructions on the AOAI Web Browsing MCP GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with AOAI Web Browsing MCP?
AOAI Web Browsing MCP works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is AOAI Web Browsing MCP free to use?
Yes, AOAI Web Browsing MCP is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
AOAI Web Browsing MCP Alternatives — Similar Browser Automation Servers
Looking for alternatives to AOAI Web Browsing MCP? Here are other popular browser automation servers you can use with Claude, Cursor, and VS Code.
Chrome DevTools MCP
★ 40.6kAI-powered Chrome automation server with natural language element detection. Control Chrome browser through MCP protocol for testing, debugging, and performance analysis. Features 91% accuracy in element location, works with free AI models, and suppo
UI TARS Desktop
★ 34.9k📇 🏠 - Browser automation capabilities using Puppeteer, both support local and remote browser connection.
Playwright
★ 32.8kA production-ready browser automation server that enables AI assistants to interact with web pages using tools for navigation, element interaction, and data extraction. It features a built-in Inspector UI and robust crash recovery for reliable automa
Page Agent
★ 18.0kJavaScript in-page GUI agent. Control web interfaces with natural language.
Chrome
★ 11.7kAn extension-based MCP server that enables AI assistants to control your browser, leveraging existing sessions and login states for automation and content analysis. It provides over 20 tools for semantic tab search, interactive element manipulation,
LAMDA
★ 7.8kThe most powerful Android RPA agent framework, next generation mobile automation.
Browse More Browser Automation MCP Servers
Explore all browser automation servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up AOAI Web Browsing 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 AOAI Web Browsing MCP?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.