browser-use-cloud-mcp

# Browser Use Cloud MCP Server A Model Context Protocol (MCP) server that provides access to the Browser Use Cloud API for automated browser tasks and web automation. ## Features - ✅ Complete implementation of all Browser Use Cloud API endpoints - ✅ Support for both stdio and HTTP transports - ✅ Comprehensive error handling and validation - ✅ Full type safety with Pydantic models - ✅ Async/await support throughout - ✅ Detailed logging and debugging capabilities - ✅ Extensive test coverage ## Installation ### From PyPI (when published) ```bash pip install browser-use-cloud-mcp ``` ### From Source ```bash git clone https://github.com/fere-ai/browser-use-cloud-mcp.git cd browser-use-cloud-mcp pip install . ``` ### For Development ```bash git clone https://github.com/fere-ai/browser-use-cloud-mcp.git cd browser-use-cloud-mcp poetry install ``` ### Alternative Development Installation (if Poetry has permission issues) If you encounter permission errors with Poetry when installing packages, you can use a standard Python virtual environment instead: ```bash git clone https://github.com/fere-ai/browser-use-cloud-mcp.git cd browser-use-cloud-mcp python -m venv .venv source .venv/bin/activate pip install -e . pip install pytest pytest-asyncio pytest-mock black isort mypy ruff jsonschema ``` ## Configuration Set your Browser Use Cloud API key as an environment variable: ```bash export BROWSER_USE_CLOUD_API_KEY="your-api-key-here" ``` Get your API key from [Browser Use Cloud](https://cloud.browser-use.com/). ### Optional: Default LLM Model You can set a default LLM model that will be used for all tasks when no model is explicitly specified: ```bash export BROWSER_USE_CLOUD_DEFAULT_MODEL="gpt-4o" ``` Valid model options: - `gpt-4o` - `gpt-4o-mini` - `gpt-4.1` - `gpt-4.1-mini` - `gemini-2.0-flash` - `gemini-2.0-flash-lite` - `gemini-2.5-flash-preview-04-17` - `claude-3-7-sonnet-20250219` - `claude-sonnet-4-20250514` - `llama-4-maverick-17b-128e-instruct` When a …