This repository demonstrates how to build intelligent web automation agents using Amazon Nova Act integrated with MCP (Model Context Protocol). MCP provides a standardized way to connect AI models to different data sources and tools - think of it like a "USB-C port for AI applications."
This project showcases the integration between:
- Amazon Nova Act: A powerful web automation tool for creating agents that interact with web pages
- MCP (Model Context Protocol): An open protocol that standardizes how applications provide context to LLMs
- Amazon Bedrock: Managed service that provides foundation models through a unified API
The project follows MCP's client-server architecture:
- MCP Host: Claude Desktop or other AI tools that want to access Nova Act capabilities
- MCP Client: Protocol clients maintaining 1:1 connections with the Nova Act server
- MCP Server: A Nova Act server exposing web automation capabilities through the standardized protocol
- Remote Services: Web services that Nova Act interacts with through browser automation
- Standardized LLM integration through MCP
- Automated web navigation and interaction via Nova Act
- Parallel execution of multiple browser tasks
- Data extraction and processing
- Screenshot capture and visual verification
- Session management and browser control
- Seamless integration with Claude Desktop
- Access to foundation models via Amazon Bedrock
- Operating System: MacOS or Ubuntu (Nova Act requirements)
- Python 3.10 or higher
- A valid Nova Act API key (obtain from
https://nova.amazon.com/act) - Node.js (for Claude Desktop integration)
- Amazon Bedrock access:
Amazon Bedrock enabled in your AWS account - Claude 3.5 Sonnet V2 model enabled (this is default for this example)
- AWS credentials and region properly configured -
AWS CLI Quickstart Guide
The repository contains two main example directories:
video_game_research_st.py
: A comprehensive tool that:- Finds top games for any selected gaming system
- Searches Amazon in parallel for pricing and details
- Creates interactive result tables
- Saves research data for future reference
nova_act_mcp_server.py
: MCP-compliant server implementation exposing Nova Act capabilitiesnova_act_mcp_client.py
: Example MCP client implementation- Demonstrates integration with Claude Desktop and other MCP hosts
get_coffee_maker.py
: Simple example demonstrating how to:- Initialize Nova Act with a starting web page
- Perform basic web search and selection actions
- Extract information from product pages
multi_monitor.py
: Advanced example showing:- Parallel execution of web tasks using ThreadPoolExecutor
- Searching and comparing multiple products simultaneously
- Structured data extraction and comparison
- Error handling for robust web automation
-
Clone this repository
-
Install dependencies:
pip install -r requirements.txt
-
Set your Nova Act API key:
export NOVA_ACT_API_KEY="your_api_key"
-
Make sure your environment has AWS configured correctly -
https://docs.aws.amazon.com/cli/latest/userguide/getting-started-quickstart.html
cd streamlit_examples
streamlit run video_game_research_st.py
cd mcp_examples
python nova_act_mcp_client.py nova_act_mcp_server.py
The command above will:
- Start the MCP server that exposes Nova Act capabilities
- Launch the MCP client that connects to the server
- Enable communication between Claude and the Nova Act browser automation
For setting up and using this server with Claude Desktop, please follow the official
- Installing and configuring Claude Desktop
- Setting up MCP servers in Claude Desktop
- Troubleshooting common issues
- Example usage and best practices
- Follow MCP's standardized approach for exposing capabilities
- Always close browser sessions when done
- Use headless mode for automated tasks not requiring visual feedback
- Break down complex actions into smaller, specific instructions
- Use schemas when expecting structured data responses
- Save important results to files for persistence
- Handle errors appropriately in your code
See CONTRIBUTING for more information.
This library is licensed under the MIT-0 License. See the LICENSE file.
MCP Documentation Nova Act Documentation Amazon Bedrock Documentation