Cumulocity IoT
A Python-based server that provides Cumulocity IoT platform functionality through the MCP (Model Control Protocol) interface.
What is Cumulocity IoT?
Cumulocity IoT is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to python-based server that provides cumulocity iot platform functionality through the mcp (model control protocol) interface.
A Python-based server that provides Cumulocity IoT platform functionality through the MCP (Model Control Protocol) interface.
This server falls under the Cloud Services category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- A Python-based server that provides Cumulocity IoT platform
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx cumulocityConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Cumulocity IoT
The Cumulocity IoT MCP Server connects AI assistants to the Cumulocity IoT platform, enabling natural language queries and management of connected devices, measurements, alarms, and dynamic mapper expressions. It ships as a Python package installable via pip or uvx, and supports both Claude Desktop and Cursor IDE through stdio transport.
Prerequisites
- A Cumulocity IoT tenant with a valid username and password
- Python 3.10+ with pip, or uv installed for the uvx installation method
- Claude Desktop or Cursor IDE as your MCP client
- The Cumulocity base URL for your tenant (e.g. https://your-tenant.cumulocity.com)
Install the Cumulocity MCP server package
Install the mcp-server-c8y package using pip or uv. The uvx method is the simplest approach as it automatically manages the Python environment for you.
# Using pip
pip install mcp-server-c8y
# Verify the installation
python -m mcp_server_c8y --helpGather your Cumulocity credentials
Collect the four required credentials: your tenant base URL, tenant identifier, username, and password. These are passed as environment variables to the MCP server. Never hardcode credentials in configuration files committed to version control.
# Export credentials for local testing
export C8Y_BASEURL="https://your-tenant.cumulocity.com"
export C8Y_TENANT="your-tenant-id"
export C8Y_USER="your-username"
export C8Y_PASSWORD="your-password"
# Test the connection manually
uvx mcp-server-c8y --transport stdioAdd the server to Claude Desktop
Edit claude_desktop_config.json to register the Cumulocity MCP server using uvx. This ensures the correct Python package version is used without manual virtual environment management. Restart Claude Desktop after saving.
Test device queries in Claude
Ask Claude to list your IoT devices or retrieve measurements. If the server is configured correctly, you should see real device data from your Cumulocity tenant returned in the response.
Optional: deploy as a Cumulocity microservice
For production deployments, the server can be packaged as a Cumulocity microservice using the included build script. This hosts the MCP server inside your tenant and enables Cursor to connect via the tenant URL with Basic auth.
git clone https://github.com/Cumulocity-IoT/cumulocity-mcp-server.git
cd cumulocity-mcp-server
./scripts/buildcontainer.shCumulocity IoT Examples
Client configuration
Claude Desktop configuration using uvx to run the Cumulocity MCP server. Replace all placeholder values with your actual tenant credentials.
{
"mcpServers": {
"mcp-c8y": {
"command": "uvx",
"args": ["mcp-server-c8y", "--transport", "stdio"],
"env": {
"C8Y_BASEURL": "https://your-tenant.cumulocity.com",
"C8Y_TENANT": "your-tenant-id",
"C8Y_USER": "your-username",
"C8Y_PASSWORD": "your-password"
}
}
}
}Prompts to try
Natural language prompts for querying devices, measurements, and alarms in your Cumulocity IoT tenant.
- "List all IoT devices in my Cumulocity tenant"
- "Show me the child devices of device ID 12345"
- "Get the last hour of temperature measurements for device 12345"
- "Are there any active critical alarms in the system?"
- "Evaluate this JSONata expression against the device fragment: $.c8y_Hardware.serialNumber"
- "Find all devices with the fragment type c8y_IsDevice"Troubleshooting Cumulocity IoT
Authentication error: 401 Unauthorized when the server tries to connect
Double-check C8Y_BASEURL, C8Y_TENANT, C8Y_USER, and C8Y_PASSWORD. The tenant ID is not the same as your username — it is a short string like 't12345678' found in your Cumulocity account settings. Verify credentials by logging into the Cumulocity web UI.
uvx: command not found
Install uv using: `curl -LsSf https://astral.sh/uv/install.sh | sh` then restart your terminal. Alternatively install the package directly with pip: `pip install mcp-server-c8y` and use `python -m mcp_server_c8y` as the command in the config.
Device queries return empty results even though devices exist in the tenant
Check that the C8Y_USER account has read permissions on the Inventory and Measurement APIs in Cumulocity. Also verify C8Y_BASEURL does not have a trailing slash. If using a Cumulocity EU or US region, make sure the URL matches your actual region endpoint.
Frequently Asked Questions about Cumulocity IoT
What is Cumulocity IoT?
Cumulocity IoT is a Model Context Protocol (MCP) server that python-based server that provides cumulocity iot platform functionality through the mcp (model control protocol) interface. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Cumulocity IoT?
Follow the installation instructions on the Cumulocity IoT GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Cumulocity IoT?
Cumulocity IoT works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Cumulocity IoT free to use?
Yes, Cumulocity IoT is open source and available under the Apache-2.0 license. You can use it freely in both personal and commercial projects.
Cumulocity IoT Alternatives — Similar Cloud Services Servers
Looking for alternatives to Cumulocity IoT? Here are other popular cloud services servers you can use with Claude, Cursor, and VS Code.
Open WebUI
★ 138.2kUser-friendly AI Interface (Supports Ollama, OpenAI API, ...)
Anything LLM
★ 60.4kThe all-in-one AI productivity accelerator. On device and privacy first with no annoying setup or configuration.
LocalAI
★ 46.4kLocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.
Nacos
★ 33.0kan easy-to-use dynamic service discovery, configuration and service management platform for building AI cloud native applications.
Xiaozhi ESP32
★ 26.7k本项目为xiaozhi-esp32提供后端服务，帮助您快速搭建ESP32设备控制服务器。Backend service for xiaozhi-esp32, helps you quickly build an ESP32 device control server.
Gateway
★ 11.8kA blazing fast AI Gateway with integrated guardrails. Route to 1,600+ LLMs, 50+ AI Guardrails with 1 fast & friendly API.
Browse More Cloud Services MCP Servers
Explore all cloud services servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Cumulocity IoT in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Cumulocity IoT?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.