MCP Sensor Observability

Overview

This section demonstrates how MCP-based applications generate observability events when interacting with tools, resources, and prompts.

Python and TypeScript clients interact with an MCP server that is integrated with the BlueRock sensor for observability.

These interactions emit structured events that are captured and visualized in CloudWatch.

The following operations are validated:

• Tool discovery and execution

• Resource listing and access

• Prompt discovery and execution

---

Deploying Python MCP Applications with BlueRock Sensor

---

Prerequisites

# Connect to the BlueRock EC2 instance
ssh -i bluerock-ec2-key.pem ec2-user@<instance-ip>

# Verify Python version
python3 --version

Python 3.10 or higher is required for FastMCP.

Setup

1. Install uv

curl -LsSf https://astral.sh/uv/install.sh | sh

1. Create Project Directory

Create a new project directory for MCP observability and navigate into it.

cd ~
uv init mcp-observability
cd mcp-observability

---

1. Install Required Dependencies

Install MCP framework, BlueRock sensor, and BlueRock runtime required for generating and exporting observability events.

# Create virtual environment
uv venv --python python3.12

# Activate virtual environment
source .venv/bin/activate

# Install MCP framework
uv pip install fastmcp

# Install BlueRock runtime
uv pip install /opt/bluerock/python-dist/bluepython-0.0.1-py3-none-any.whl

# Initialize BlueRock
python -m bluepython --install

---

1. Add MCP Application File

Create the MCP client and server scripts in the project directory using the sample code provided in the Appendix section.

vi mcp_client.py
vi mcp_fileserver_stdio.py
vi mcp_fileserver.py

---

1. Verify Project Files

Ensure the required files are present in the directory.

ls

Expected Output:

mcp_client.py
mcp_fileserver_stdio.py
mcp_fileserver.py

---

1. Start MCP Server

Run the MCP server to start accepting client requests.

uv run mcp_fileserver.py

Observability

---

Tool Events

Tool Listing & Execution

Command

python3 mcp_client.py \
--mcp_server http://0.0.0.0:8001/mcp \
--mcp_auth_token dev-token \
tools --list

python3 mcp_client.py \
--mcp_server http://0.0.0.0:8001/mcp \
--mcp_auth_token dev-token \
tools --tool_cmd write_file \
--tool_args '{"filename":"test.txt","content":"hello"}'

Output

Tool interactions are captured in AWS CloudWatch telemetry logs. These logs include:

• MCP client request activity

• MCP server request handling

• Tool name and arguments

• Runtime metadata

---

Resource Events

Resource Listing & Access

Command

python3 mcp_client.py \
--mcp_server http://0.0.0.0:8001/mcp \
--mcp_auth_token dev-token \
resources --list

python3 mcp_client.py \
--mcp_server http://0.0.0.0:8001/mcp \
--mcp_auth_token dev-token \
resources --resource_uri folder://explorer

Output

Resource interactions are captured in CloudWatch telemetry logs and include:

• resource name

• resource type

• resource URI

---

Prompt Events

Prompt Listing & Execution

Command

python3 mcp_client.py \
--mcp_server http://0.0.0.0:8001/mcp \
--mcp_auth_token dev-token \
prompts --list

python3 mcp_client.py \
--mcp_server http://0.0.0.0:8001/mcp \
--mcp_auth_token dev-token \
prompts --prompt_name useful_helper_prompt

Output

Prompt interactions are captured in CloudWatch telemetry logs and include:

• prompt name

• input arguments

• request flow

---

Deploying JS/TS MCP Applications with BlueRock Sensor

---

Prerequisites

Install Node.js (using NVM)

# Install NVM
curl -o- https://raw.githubusercontent.com/nvm-sh/nvm/v0.39.7/install.sh | bash

export NVM_DIR="$HOME/.nvm"
[ -s "$NVM_DIR/nvm.sh" ] && \. "$NVM_DIR/nvm.sh"

# Install Node.js
nvm install 20

# Verify installation
node -v
npm -v

Setup

1. Create Project Directory

Create a new project directory for the MCP JavaScript/TypeScript application and navigate into it.

cd ~
mkdir mcp-observability
cd mcp-observability

2.Install Dependencies

Install the required Node.js dependencies before executing the MCP scripts.

# Install BlueRock JS runtime
npm install /opt/bluerock/bluejs-dist/bluejs-0.0.1.tgz

3. Add MCP Application Files

Create the MCP client and server scripts directly on the EC2 instance using the sample code provided in the Appendix section.

mkdir tests && cd tests

vi mcp_client.js
vi mcp_fileserver.js
vi mcp_fileserver_stdio.js
vi package.json

npm install

4. Verify Project Files

Verify that the required files are present.

ls

Expected output:

mcp_client.js
mcp_fileserver.js
mcp_fileserver_stdio.js
node_modules
package-lock.json
package.json

---

Observability

To view MCP observability events in AWS CloudWatch, start the MCP server and then run the MCP client to list and execute tools.

Tool Events

Tool Listing & Execution

# Starting the MCP file server (JavaScript/TypeScript)
# Run the MCP server to start accepting client requests.
node --import bluejs tests/mcp_fileserver.js

node --import bluejs tests/mcp_client.js \
--mcp_server http://0.0.0.0:8001/mcp \
--mcp_auth_token dev-token \
tools --list

node --import bluejs tests/mcp_client.js \
--mcp_server http://0.0.0.0:8001/mcp \
--mcp_auth_token dev-token \
tools \
--tool_cmd write_file \
--tool_args '{"filename":"event-final.txt","content":"check"}'

Output

Tool interactions are captured in AWS CloudWatch telemetry logs. These logs include:

• MCP client request activity

• MCP server request handling

• Tool name and arguments

• Runtime metadata

---

Resource Events

Resource Listing & Access

cd ~/mcp-observability

node --import bluejs tests/mcp_client.js \
--mcp_server http://0.0.0.0:8001/mcp \
--mcp_auth_token dev-token \
resources --list

node --import bluejs tests/mcp_client.js \
--mcp_server http://0.0.0.0:8001/mcp \
--mcp_auth_token dev-token \
resources \
--resource_uri folder://explorer

Output

Resource interactions are captured in AWS CloudWatch telemetry logs. These logs include:

• MCP client request activity

• MCP server request handling

• Resource name and type

• Resource URI

• Runtime metadata

---

Prompt Events

Prompt Listing & Execution

cd ~/mcp-observability

node --import bluejs tests/mcp_client.js \
--mcp_server http://0.0.0.0:8001/mcp \
--mcp_auth_token dev-token \
prompts --list

node --import bluejs tests/mcp_client.js \
--mcp_server http://0.0.0.0:8001/mcp \
--mcp_auth_token dev-token \
prompts \
--prompt_name useful_helper_prompt \
--prompt_args '{"lang":"java"}'

Output

Prompt interactions are captured in AWS CloudWatch telemetry logs. These logs include:

• MCP client request activity

• MCP server request handling

• Prompt name

• Input arguments

• Runtime metadata