Litmus

The Litmus MCP Server enables large language models and intelligent systems to interact with Litmus Edge for device configuration, monitoring, and management. Built to follow the Model Context Protocol, it provides a standardized way for clients to discover, control, and observe Litmus Edge resources through a secure, scalable interface.

How to use

You connect to the MCP server from your MCP client and begin by selecting a server endpoint to establish a streaming or request/response channel. Use the provided HTTP SSE interface to receive model context updates in real time, or run the server locally and interact via standard input/output transports. Your client can perform device management, data retrieval, digital twin operations, and system health checks through the available endpoints.

How to install

Prerequisites you need before starting: ensure Docker is installed on your host system if you plan to run the server in a container. If you prefer a local runtime, you should have Python and related tooling available if you opt to run the server directly from source.

# Start the MCP server in Docker (HTTP SSE only)
docker run -d --name litmus-mcp-server -p 8000:8000 ghcr.io/litmusautomation/litmus-mcp-server:latest

# If running on ARM64 while the server is built for linux/AMD64, specify the platform
 docker run -d --name litmus-mcp-server --platform linux/amd64 -p 8000:8000 ghcr.io/litmusautomation/litmus-mcp-server:main

Configuration and usage notes

You can configure clients to connect via HTTP SSE or STDIO. The server exposes an SSE endpoint at an address like http://<MCP_SERVER_IP>:8000/sse. For local development, you can also run the server as a standard process and connect Claude Desktop or other clients through STDIO transports.

Security and environment groundwork

When connecting to Litmus Edge through the MCP server, you typically supply security credentials and connection details as part of your client configuration. The configuration often includes endpoints, OAuth2 credentials, and access tokens that authorize actions against Litmus Edge and InfluxDB. Maintain secure storage for tokens and rotate credentials as needed.

Tools and endpoints you can use with the MCP server

The MCP server provides a suite of endpoints and tool functions to manage devices, digital twins, events, and data streams. You can request current values, historical data, and perform actions such as creating devices, managing containers, and listing digital twin models.

Available tools

get_litmusedge_driver_list

List supported Litmus Edge drivers (e.g., ModbusTCP, OPCUA, BACnet).

get_devicehub_devices

List all configured DeviceHub devices with connection settings and status.

create_devicehub_device

Create a new device with a given driver and default configuration.

get_devicehub_device_tags

Retrieve all tags (data points/registers) for a specific device.

get_current_value_of_devicehub_tag

Read the current real-time value of a specific device tag.

get_litmusedge_friendly_name

Get the human-readable name assigned to the Litmus Edge device.

set_litmusedge_friendly_name

Update the friendly name of the Litmus Edge device.

get_cloud_activation_status

Check cloud registration and Litmus Edge Manager connection status.

get_all_containers_on_litmusedge

List all Docker containers running on Litmus Edge Marketplace.

run_docker_container_on_litmusedge

Deploy and run a Docker container on Litmus Edge Marketplace.

get_current_value_from_topic

Subscribe to a NATS topic and return the next published message.

get_multiple_values_from_topic

Collect multiple sequential values from a NATS topic for trend analysis.

get_historical_data_from_influxdb

Query historical time-series data from InfluxDB by measurement and time range.

list_digital_twin_models

List all Digital Twin models with ID, name, description, and version.

list_digital_twin_instances

List all Digital Twin instances or filter by model ID.

create_digital_twin_instance

Create a new Digital Twin instance from an existing model.

list_static_attributes

List static attributes for a model or instance.

list_dynamic_attributes

List dynamic attributes for a model or instance.

list_transformations

List data transformation rules configured for a Digital Twin model.

get_digital_twin_hierarchy

Get the hierarchy configuration for a Digital Twin model.

save_digital_twin_hierarchy

Save a new hierarchy configuration to a Digital Twin model.