Quick Start

Access the BlueRock Secure MCP Server on AWS using the Full BlueRock AMI. This environment establishes a secure baseline for executing applications within the BlueRock Sandbox. Unlike the Free tier, the Full deployment supports custom security configurations via the TREX tool, enabling notifications of active attack and inline blocking. The Full AMI comes preloaded with a working Weather Forecast MCP server to help establish a secure connection and test functionality immediately.

Follow these steps to access the environment and execute the example process:

1. Connect to the BlueRock Instance

2. Launch the Weather MCP Server

3. Connect the Weather MCP Client

4. Test the Weather MCP

---

Connect to the BlueRock Instance

With the AWS EC2 instance running the Full BlueRock AMI, establish a connection to access the environment.

Log in using the default ec2-user username and the SSH key specified during the instance launch:

ssh -i </path/to/key>.pem ec2-user@<INSTANCE_PUBLIC_IP>

Launch the Weather MCP Server

Once logged in, the BlueRock Sandbox binary is pre-installed at /opt/bluerock/bin/brace. In the Full tier, the Sandbox actively enforces custom security policies defined through the TREX policy manager to provide inline blocking against unauthorized actions.

Navigate to the preloaded Weather MCP directory, activate the Python virtual environment, and use the sandbox to launch the server:

cd /opt/bluerock/mcp/weatherMCP
source .venv/bin/activate

# Launch the server securely inside the BlueRock Sandbox
/opt/bluerock/bin/brace -l server.log -- uv run server-weatherMCP.py

• -l: Specifies the path to create the local log file for sandbox execution data.

• --: Separates the sandbox configurations from the target application's execution command.

Connect the Weather MCP Client

Open a new, separate terminal window on the local machine and log into the EC2 instance again using the same SSH command from the first step.

Once connected, navigate to the Weather MCP directory, activate the virtual environment, and start the interactive client:

cd /opt/bluerock/mcp/weatherMCP
source .venv/bin/activate

# Launch the interactive client
uv run client-weatherMCP.py

Upon successful connection, the console will display a weather> prompt and a list of available tools.

Test the Weather MCP

With the interactive client running, execute commands to retrieve real-time weather data from the sandboxed server. For example, to fetch active weather alerts for California, enter the following at the prompt:

weather> alerts CA

Expected Output Snippet:

[10/31/25 15:49:46] INFO Processing request of type CallToolRequest server.py:674
============================================================
WEATHER ALERTS
============================================================
Event: Beach Hazards Statement
Area: San Francisco; Coastal North Bay Including Point Reyes National Seashore...
Severity: Moderate
Description: * WHAT...A long period northwesterly swell will result in an
increased risk for sneaker waves...

To view all available commands, type help. To exit the client, type quit.