What is Nova Act Mcp

nova-act-mcp-server is a zero-install Model Context Protocol (MCP) server designed to integrate Amazon Nova Act browser-automation tools for AI agents, allowing for seamless interaction and automation within web environments.

Use cases

This tool is ideal for AI agents seeking to automate browser actions, such as filling forms, navigating web pages, capturing screenshots, and executing natural language instructions directly in a browser context.

How to use

To use nova-act-mcp-server, first obtain an API key from Nova Act. Then, add the server configuration to your MCP client and start it. AI agents can access browser tools like start_session and execute_instruction through any MCP-compatible client.

Key features

Key features include file-based screenshots to bypass message size limits, optimized image quality for smaller file sizes, enhanced error handling for browser operations, comprehensive test coverage, and MCP Inspector integration for easy testing.

Where to use

You can use nova-act-mcp-server in any MCP-compatible environment, such as Claude Desktop or VS Code, enabling AI agents to perform web automation tasks efficiently across various projects.

nova-act-mcp-server

nova‑act‑mcp‑server is a zero‑install Model Context Protocol (MCP) server that exposes Amazon Nova Act browser‑automation tools for AI agents.

What’s New in v3.2.0

• File-Based Screenshots: Screenshots now save to files instead of inline base64, eliminating MCP message size limits
• Optimized Image Quality: Reduced screenshot quality (60/30) for smaller file sizes (~50KB vs 500KB+)
• Enhanced Error Handling: Improved exception handling for browser operations
• Better Testing: Comprehensive test coverage for screenshot functionality
• MCP Inspector Integration: New testing script for easy validation

Quick Start (uvx)

Step 1: Get a Nova Act API Key

Obtain your API key from Nova Act.

Step 2: Add to MCP Client Configuration

{
  "mcpServers": {
    "nova_act_browser_tools": {
      "command": "uvx",
      "args": ["nova-act-mcp-server"],
      "env": { "NOVA_ACT_API_KEY": "YOUR_NOVA_ACT_API_KEY_HERE" }
    }
  }
}

Step 3: Start Using Browser Tools

AI agents can now call tools like start_session, execute_instruction, etc. through any MCP-compatible client such as Claude Desktop or VS Code.

Core Tools Overview

Local Development & Testing

Setup

# Clone the repository
git clone https://github.com/madtank/nova-act-mcp.git
cd nova-act-mcp

# Create and activate virtual environment
uv venv
source .venv/bin/activate  # On Windows: .venv\Scripts\activate

# Install with development dependencies
uv pip install -e .[dev]

Running Tests

# Run all tests (integration tests require NOVA_ACT_API_KEY)
pytest

# Run only unit tests (no API key required)
pytest tests/unit

# Run integration tests (requires API key)
NOVA_ACT_API_KEY="your_key_here" pytest tests/integration

Running Locally with MCP Inspector UI

# Start the server with the MCP Inspector
npx @modelcontextprotocol/inspector -e PYTHONUNBUFFERED=1 -e NOVA_ACT_API_KEY="YOUR_KEY" -- python -m nova_mcp_server

Then visit http://localhost:6274 in your browser. For optimal experience, set the Inspector UI timeout to 60 seconds for start_session operations.

Advanced Tools

License

MIT