Amazon Nova Agents
Discover how to build agents that can perform actions on websites by combining Amazon Nova Act with Model Context Protocol (MCP).
What is Amazon Nova Agents?
Amazon Nova Agents is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to discover how to build agents that can perform actions on websites by combining amazon nova act with model context protocol (mcp).
Discover how to build agents that can perform actions on websites by combining Amazon Nova Act with Model Context Protocol (MCP).
This server falls under the Coding Agents category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Discover how to build agents that can perform actions on web
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx sample-agents-with-nova-act-andConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Amazon Nova Agents
The Amazon Nova Agents MCP server is a sample project demonstrating how to build web-automation agents by combining Amazon Nova Act with the Model Context Protocol. It lets LLMs drive real browsers in parallel via Nova Act sessions, capture screenshots for visual verification, and extract structured data from websites — all while orchestrating those tasks through AWS Bedrock. Developers use it to learn how agentic browser workflows can be composed with MCP and Amazon Bedrock services.
Prerequisites
- macOS or Ubuntu (Python 3.10+ required)
- Amazon Nova Act API key from https://nova.amazon.com/act
- AWS account with Amazon Bedrock enabled and Claude 3.5 Sonnet V2 model access granted
- Configured AWS credentials (via AWS CLI or environment variables)
- An MCP-compatible client such as Claude Desktop
Clone the repository
Clone the aws-samples repository to your local machine and navigate into it.
git clone https://github.com/aws-samples/sample-agents-with-nova-act-and-mcp
cd sample-agents-with-nova-act-and-mcpInstall Python dependencies
Create a virtual environment and install all required packages from requirements.txt.
python -m venv .venv
source .venv/bin/activate
pip install -r requirements.txtSet environment variables
Export your Nova Act API key and configure AWS credentials so both Nova Act and Bedrock can authenticate.
export NOVA_ACT_API_KEY="your-nova-act-api-key"
export AWS_ACCESS_KEY_ID="your-access-key-id"
export AWS_SECRET_ACCESS_KEY="your-secret-access-key"
export AWS_DEFAULT_REGION="us-east-1"Run the MCP server
Start the Nova Act MCP server from the mcp_examples directory. It exposes browser automation capabilities over the MCP protocol for an LLM client to call.
cd mcp_examples
python nova_act_mcp_client.py nova_act_mcp_server.pyConfigure Claude Desktop
Add the server to Claude Desktop's configuration file so it is available as an MCP tool.
Try the Streamlit demo (optional)
Run the included Streamlit example to see parallel browser automation — it finds top video games and searches Amazon for pricing simultaneously.
cd streamlit_examples
streamlit run video_game_research_st.pyAmazon Nova Agents Examples
Client configuration
Add the Nova Act MCP server to Claude Desktop's config file. Adjust the Python path and project directory to match your local setup.
{
"mcpServers": {
"nova-act-agent": {
"command": "/path/to/.venv/bin/python",
"args": ["/path/to/sample-agents-with-nova-act-and-mcp/mcp_examples/nova_act_mcp_server.py"],
"env": {
"NOVA_ACT_API_KEY": "your-nova-act-api-key",
"AWS_DEFAULT_REGION": "us-east-1"
}
}
}
}Prompts to try
Once connected, ask the agent to perform real browser tasks using Nova Act and Bedrock.
- "Search Amazon for the top 3 PS5 games released this year and return their prices."
- "Open the AWS console, navigate to S3, and list all my bucket names."
- "Take a screenshot of the Wikipedia homepage and describe what you see."
- "Find pricing for the MacBook Pro M4 across three different websites in parallel."Troubleshooting Amazon Nova Agents
NOVA_ACT_API_KEY not recognized or authentication fails
Ensure the key is exported in the same shell session or set in the env block of the MCP config. Verify the key at https://nova.amazon.com/act under your account settings.
Bedrock model access denied when running the agent
Go to the AWS Bedrock console, open 'Model access', and request access to Claude 3.5 Sonnet V2 in your chosen region. Access is not granted by default.
Browser sessions hang or time out during parallel execution
Nova Act spawns real browser processes; ensure your machine has enough RAM and that no firewall blocks outbound browser traffic. Reduce parallelism by lowering the ThreadPoolExecutor max_workers in the server code.
Frequently Asked Questions about Amazon Nova Agents
What is Amazon Nova Agents?
Amazon Nova Agents is a Model Context Protocol (MCP) server that discover how to build agents that can perform actions on websites by combining amazon nova act with model context protocol (mcp). It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Amazon Nova Agents?
Follow the installation instructions on the Amazon Nova Agents GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Amazon Nova Agents?
Amazon Nova Agents works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Amazon Nova Agents free to use?
Yes, Amazon Nova Agents is open source and available under the MIT-0 license. You can use it freely in both personal and commercial projects.
Amazon Nova Agents Alternatives — Similar Coding Agents Servers
Looking for alternatives to Amazon Nova Agents? Here are other popular coding agents servers you can use with Claude, Cursor, and VS Code.
Dify
★ 142.2kProduction-ready platform for agentic workflow development.
Ruflo
★ 54.0k🌊 The leading agent orchestration platform for Claude. Deploy intelligent multi-agent swarms, coordinate autonomous workflows, and build conversational AI systems. Features enterprise-grade architecture, self-learning swarm intelligence, RAG integrat
Goose
★ 45.7kan open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM
Antigravity Awesome Skills
★ 38.3kInstallable GitHub library of 1,400+ agentic skills for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and more. Includes installer CLI, bundles, workflows, and official/community skill collections.
AgentScope
★ 25.5kBuild and run agents you can see, understand and trust.
Serena
★ 24.5kA coding agent toolkit that provides IDE-like semantic code retrieval and editing tools, enabling LLMs to efficiently navigate and modify codebases using symbol-level operations instead of basic file reading and string replacements.
Browse More Coding Agents MCP Servers
Explore all coding agents servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Amazon Nova Agents 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 Amazon Nova Agents?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.