pyBTMCP
A BLE fitness device simulator that enables AI agents to control simulated heart rate monitors, treadmills, and cycling trainers via the Model Context Protocol. It integrates ESP32 firmware, an MQTT broker, and a FastAPI backend for comprehensive device management and real-time interaction.
README
pyBTMCP - BLE Device Simulator with MCP Integration
A comprehensive BLE (Bluetooth Low Energy) fitness device simulator that enables AI agents like Claude to control simulated heart rate monitors, treadmills, and cycling trainers via the Model Context Protocol (MCP).
Overview
pyBTMCP consists of three integrated components:
- ESP32 Firmware - Runs on ESP32 microcontrollers to simulate BLE fitness devices
- Python Backend - FastAPI server with MQTT broker for device communication
- MCP Server - Enables Claude and other AI agents to control devices
┌─────────────────┐ ┌──────────────────────────────────────────┐
│ Claude/AI │ │ Docker Container │
│ (MCP Client) │◄───►│ ┌─────────┐ ┌───────┐ ┌──────────┐ │
└─────────────────┘ │ │ MCP │ │ MQTT │ │ FastAPI │ │
│ │ Server │◄►│Broker │◄►│ + Web │ │
│ └─────────┘ └───┬───┘ └──────────┘ │
└──────────────────│───────────────────────┘
│
┌──────────────────▼───────────────────────┐
│ ESP32 Devices │
│ ┌─────────┐ ┌─────────┐ ┌─────────┐ │
│ │ HR │ │Treadmill│ │ Bike │ │
│ │ Monitor │ │ │ │ Trainer │ │
│ └─────────┘ └─────────┘ └─────────┘ │
└──────────────────────────────────────────┘
Quick Start
Prerequisites
- Docker
- (Optional) ESP32 development board for hardware simulation
1. Build the Docker Image
docker build -t pybtmcp:latest .
2. Run the Container
docker run -it --rm \
-p 1883:1883 \
-p 8000:8000 \
--name pybtmcp \
pybtmcp:latest
This starts:
- MQTT Broker on port 1883 (for ESP32 device connections)
- Web UI / API on port 8000 (browser interface)
- MCP Server on stdio (for Claude integration)
3. Access the Web UI
Open http://localhost:8000 in your browser to see connected devices and control them manually.
MCP Integration (Claude Desktop)
To use pyBTMCP with Claude Desktop, add it to your MCP configuration:
Configuration File Location
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%\Claude\claude_desktop_config.json
Add the Server Configuration
{
"mcpServers": {
"ble-simulator": {
"command": "docker",
"args": [
"run", "-i", "--rm",
"-p", "1883:1883",
"-p", "8000:8000",
"--name", "pybtmcp",
"pybtmcp:latest"
]
}
}
}
Restart Claude Desktop
After saving the configuration, restart Claude Desktop. You should see the "ble-simulator" MCP server available.
MCP Integration (Claude Code CLI)
To add pyBTMCP to Claude Code, run:
claude mcp add ble-simulator \
-s user \
-- docker run -i --rm -p 1883:1883 -p 8000:8000 --name pybtmcp pybtmcp:latest
This adds the MCP server to your user configuration. Use -s project instead to add it to the current project only.
To verify the server was added:
claude mcp list
MCP Tools Reference
Once configured, Claude can use these tools to control BLE devices:
list_devices
List all connected ESP32 BLE simulator devices.
No parameters required
configure_device
Configure an ESP32 to simulate a specific BLE device type.
| Parameter | Type | Required | Description |
|---|---|---|---|
| device_id | string | Yes | The ESP32 device ID |
| device_type | string | Yes | One of: heart_rate, treadmill, bike |
set_heart_rate
Set the simulated heart rate for a heart rate monitor device.
| Parameter | Type | Required | Description |
|---|---|---|---|
| device_id | string | Yes | The ESP32 device ID |
| bpm | integer | Yes | Heart rate (30-220 BPM) |
set_treadmill_values
Set simulated values for a treadmill device.
| Parameter | Type | Required | Description |
|---|---|---|---|
| device_id | string | Yes | The ESP32 device ID |
| speed | number | No | Speed in km/h (0-25) |
| incline | number | No | Incline percentage (-5 to 30) |
set_bike_values
Set simulated values for a bike/cycling trainer device.
| Parameter | Type | Required | Description |
|---|---|---|---|
| device_id | string | Yes | The ESP32 device ID |
| power | integer | No | Power in watts (0-2000) |
| cadence | integer | No | Cadence in RPM (0-200) |
| speed | number | No | Speed in km/h (0-80) |
get_device_status
Get the current status and values of a specific device.
| Parameter | Type | Required | Description |
|---|---|---|---|
| device_id | string | Yes | The ESP32 device ID |
Web UI Features
The web interface at http://localhost:8000 provides:
- Real-time device status via WebSocket (live updates)
- Device type configuration (Heart Rate, Treadmill, Bike)
- Preset values for quick testing (Rest, Warm Up, Cardio, etc.)
- Manual sliders for fine-grained control
- Unit switching (Metric/Imperial)
- HR variation toggle for realistic heart rate simulation
Connection Status Indicator
The UI shows WebSocket connection status:
- 🟢 Live - Connected and receiving real-time updates
- 🟡 Connecting... - Attempting to connect
- 🔴 Disconnected - Using polling fallback
REST API
The FastAPI backend provides these endpoints:
| Method | Endpoint | Description |
|---|---|---|
| GET | /api/devices |
List all devices |
| GET | /api/devices/{id} |
Get device by ID |
| POST | /api/devices/{id}/configure |
Configure device type |
| POST | /api/devices/{id}/values |
Set device values |
| GET | /health |
Health check |
| WS | /ws |
WebSocket for real-time updates |
API documentation is available at http://localhost:8000/docs (Swagger UI).
ESP32 Firmware Setup
Hardware Requirements
- ESP32 development board (ESP32-DevKitC, ESP32-WROOM, etc.)
- USB cable for programming
Building the Firmware
- Install PlatformIO
- Navigate to the firmware directory:
cd firmware/esp32_ble_sim - Build and upload:
pio run -t upload
Initial Configuration
- On first boot, the ESP32 creates a WiFi access point:
BLE-Sim-XXXX - Connect to the AP and open http://192.168.4.1
- Enter your WiFi credentials and MQTT broker address
- The device will restart and connect to your network
MQTT Topics
The ESP32 devices communicate via MQTT:
| Topic | Direction | Description |
|---|---|---|
ble-sim/{id}/status |
Device → Server | Device online status |
ble-sim/{id}/values |
Device → Server | Current sensor values |
ble-sim/{id}/config |
Server → Device | Device type configuration |
ble-sim/{id}/set |
Server → Device | Set sensor values |
Development
Running Locally (without Docker)
-
Install dependencies:
pip install -r requirements.txt -
Start an MQTT broker (e.g., Mosquitto):
mosquitto -c config/mosquitto.conf -
Start the API server:
uvicorn src.api.main:app --reload --port 8000 -
Run the MCP server (for testing):
python -m src.mcp.server
Environment Variables
| Variable | Default | Description |
|---|---|---|
| MQTT_HOST | localhost | MQTT broker hostname |
| MQTT_PORT | 1883 | MQTT broker port |
Project Structure
pyBTMCP/
├── src/
│ ├── mcp/
│ │ └── server.py # MCP server implementation
│ ├── api/
│ │ ├── main.py # FastAPI app + WebSocket
│ │ ├── routes.py # REST API routes
│ │ ├── mqtt_client.py # MQTT connection manager
│ │ └── device_registry.py # Device state tracking
│ └── web/
│ └── static/
│ └── index.html # Web UI
├── firmware/
│ └── esp32_ble_sim/ # PlatformIO ESP32 project
├── config/
│ └── mosquitto.conf # MQTT broker config
├── Dockerfile
├── entrypoint.sh
├── requirements.txt
└── mcp-config.example.json # Example Claude Desktop config
Supported BLE Services
| Device Type | BLE Service | Characteristics |
|---|---|---|
| Heart Rate Monitor | Heart Rate Service (0x180D) | Heart Rate Measurement |
| Treadmill | Fitness Machine Service (0x1826) | Treadmill Data |
| Bike Trainer | Cycling Power Service (0x1818) | Cycling Power Measurement |
Troubleshooting
MCP server not appearing in Claude Desktop
- Ensure Docker is running
- Check the config file path is correct for your OS
- Restart Claude Desktop after saving config
- Check Docker logs:
docker logs pybtmcp
ESP32 not connecting
- Verify WiFi credentials are correct
- Ensure MQTT broker is reachable from ESP32's network
- Check MQTT broker is listening on port 1883
- Use
mosquitto_sub -t "ble-sim/#" -vto monitor MQTT traffic
Web UI not updating
- Check browser console for WebSocket errors
- Verify the container is running:
docker ps - The UI falls back to 5-second polling if WebSocket disconnects
License
MIT License
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.