The Things Stack MCP Server
Enables interaction with The Things Industries LoRaWAN platform via MCP tools, supporting application, device, gateway, and webhook management.
README
The Things Stack MCP Server
MCP (Model Context Protocol) Server for the The Things Stack HTTP API. This server enables interaction with The Things Industries LoRaWAN platform via standardized MCP tools.
Features
The MCP server offers a wide range of tools for managing your LoRaWAN infrastructure:
- Application Management: Create, list, delete, and inspect applications.
- Device Management: Comprehensive device lifecycle management including
create_otaa_devicewhich handles registration across Identity, Join, Network, and Application servers in one go. - Gateway Management: List, inspect, create and delete gateways.
- User Management: Retrieve user details.
- Webhook Integrations: Manage webhooks for applications to integrate with external systems.
- Messaging: View historical uplinks, simulate uplinks, and manage downlink queues.
- Payload Formatters: Generate commands to configure formatters or test them directly.
Prerequisites
- Docker and Docker Compose installed
- An account on The Things Stack or a private instance
- An API Key with appropriate permissions
Creating an API Key
- Log in to the Things Stack Console
- Go to your User Settings (Profile)
- Navigate to API Keys
- Click Add API Key
- Give it a name (e.g., "MCP Server")
- Select the following permissions:
- Applications: Read & Write
- Devices: Read & Write
- Gateways: Read & Write
- Users: Read
- Copy the generated API Key (Format:
NNSXS.XXX...)
Quick Start
# 1. Build Docker Image
docker build -t things-stack-mcp .
# 2. Test (replace placeholder values!)
export TTS_BASE_URL=https://eu1.cloud.thethings.network
export TTS_API_KEY=NNSXS.XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX
./test_server.sh
Installation & Setup
1. Clone Repository / Create Files
Ensure all files are present in the project directory:
├── server.py # MCP Server Implementation
├── requirements.txt # Python Dependencies
├── Dockerfile # Docker Image Definition
├── docker-compose.yml # Docker Compose Configuration
├── claude_desktop_config.example.json # Claude Desktop Example Config
├── test_server.sh # Test Script
├── run_example.sh # Interactive Start Script
└── README.md # This file
2. Build Docker Image
docker build -t things-stack-mcp .
3. Configuration
Available Regions:
- Europe:
https://eu1.cloud.thethings.network - North America:
https://nam1.cloud.thethings.network - Australia:
https://au1.cloud.thethings.network - Private Instance:
https://your-instance.example.com
Environment variables are passed directly in the Docker run command (see next section).
Usage
With MCP-compatible Clients
The server can be used with any MCP-compatible client (e.g., Claude Desktop App).
Claude Desktop Configuration
Add the following to your Claude Desktop configuration:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
Linux: ~/.config/Claude/claude_desktop_config.json
{
"mcpServers": {
"things-stack": {
"command": "docker",
"args": [
"run",
"--rm",
"-i",
"-e",
"TTS_BASE_URL=https://eu1.cloud.thethings.network",
"-e",
"TTS_API_KEY=NNSXS.XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX",
"things-stack-mcp"
]
}
}
}
Important: Replace NNSXS.XXX... with your actual API key and adjust the region if necessary.
Tip: You can use claude_desktop_config.example.json as a template.
Interactive Start
Use the interactive script for easy configuration:
./run_example.sh
The script will ask for your region and API key, then start the server.
Direct Test with Docker
# Start server interactively
docker run --rm -i \
-e TTS_BASE_URL=https://eu1.cloud.thethings.network \
-e TTS_API_KEY=NNSXS.XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX \
things-stack-mcp
# Example: List Applications
echo '{"jsonrpc":"2.0","method":"tools/call","params":{"name":"list_applications","arguments":{}},"id":1}' | \
docker run --rm -i \
-e TTS_BASE_URL=https://eu1.cloud.thethings.network \
-e TTS_API_KEY=NNSXS.XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX \
things-stack-mcp
Examples
Create Application
{
"name": "create_application",
"arguments": {
"user_id": "your-user-id",
"application_id": "my-app",
"name": "My Application",
"description": "Test Application"
}
}
Create OTAA Device (Recommended)
{
"name": "create_otaa_device",
"arguments": {
"application_id": "my-app",
"device_id": "my-device-01",
"name": "Sensor 01",
"description": "Temperature sensor in office",
"dev_eui": "70B3D57ED0000001",
"join_eui": "0000000000000000",
"app_key": "00112233445566778899AABBCCDDEEFF",
"lorawan_version": "MAC_V1_0_3",
"frequency_plan_id": "EU_863_870_TTN",
"supports_class_c": false
}
}
This tool executes 4 separate API calls to register the device across all required servers:
-
POST
/api/v3/applications/{app_id}/devices- Identity Server- Metadata (Name, IDs, Description)
- Server addresses
-
PUT
/api/v3/js/applications/{app_id}/devices/{device_id}- Join Server- Root Keys (AppKey for OTAA)
- Authentication
-
PUT
/api/v3/ns/applications/{app_id}/devices/{device_id}- Network Server- MAC Settings
- LoRaWAN Version & PHY Version
- Frequency Plan
- Class B/C Support
-
PUT
/api/v3/as/applications/{app_id}/devices/{device_id}- Application Server- Device IDs
- Session Configuration
Important Parameters:
app_key: 32-digit hex string (128-bit key)dev_eui&join_eui: 16-digit hex strings (64-bit)frequency_plan_id: Common values:EU_863_870_TTN- Europe (Default)US_902_928- USAAU_915_928- AustraliaAS_923- Asia
lorawan_version:MAC_V1_0_2,MAC_V1_0_3,MAC_V1_0_4,MAC_V1_1
Create Webhook
{
"name": "set_webhook",
"arguments": {
"application_id": "my-app",
"webhook_id": "my-integration",
"base_url": "https://myserver.com/webhook",
"format": "json",
"uplink_message": {
"path": "/up"
},
"join_accept": {
"path": "/join"
}
}
}
Set Payload Formatter (Command Generator)
{
"name": "generate_formatter_command",
"arguments": {
"application_id": "my-app",
"device_id": "my-device-01",
"formatter_type": "FORMATTER_JAVASCRIPT",
"formatter_code": "function decodeUplink(input) { return {data: {temp: input.bytes[0]}}; }",
"command_type": "curl"
}
}
Output: Ready-to-use cURL command to copy & execute.
Available Command Types:
curl- cURL Command (Default)cli- The Things Stack CLI Commandpython- Python Script
The tool generates ready-to-use commands that you can execute directly, as direct API calls might not work on all TTS installations.
Retrieve Uplink Data
{
"name": "get_device_uplinks",
"arguments": {
"application_id": "my-app",
"device_id": "my-device-01",
"limit": 20
}
}
Development
Local Development without Docker
# Create Virtual Environment
python3 -m venv venv
source venv/bin/activate # On Windows: venv\Scripts\activate
# Install Dependencies
pip install -r requirements.txt
# Set Environment Variables
export TTS_BASE_URL=https://eu1.cloud.thethings.network
export TTS_API_KEY=NNSXS.XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX
# Start Server
python server.py
Troubleshooting
Authentication Errors (401)
- Verify your API Key is correct
- Ensure the API Key has the required permissions
- Check if the API Key is still valid
- The API Key should start with
NNSXS.
Connection Errors
- Check
TTS_BASE_URL(must start withhttps://) - Ensure you are using the correct region
- Check your network connection
- For self-hosted instances: Check Firewall and SSL certificates
Device Creation Failed
dev_euiandjoin_euimust be valid 64-bit hex strings (16 characters)device_idmust only contain lowercase letters, numbers, and dashes- The Application must already exist
MCP Server Not Starting in Claude Desktop
- Check JSON syntax in Claude Desktop configuration
- Ensure Docker image is built:
docker build -t things-stack-mcp . - Check Docker logs:
docker logs <container-id>
API References
License
MIT
Author
Created with Claude Code
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.
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.
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.
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.