# Litmus Mcp Server > Official MCP server for configuring Litmus instances. - **Type:** MCP server - **Install:** `agentstack add mcp-litmusautomation-litmus-mcp-server` - **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior - **Seller:** [litmusautomation](https://agentstack.voostack.com/s/litmusautomation) - **Installs:** 0 - **Category:** [Integrations](https://agentstack.voostack.com/c/integrations) - **Latest version:** 0.1.0 - **License:** Apache-2.0 - **Upstream author:** [litmusautomation](https://github.com/litmusautomation) - **Source:** https://github.com/litmusautomation/litmus-mcp-server - **Website:** https://litmus.io/ ## Install ```sh agentstack add mcp-litmusautomation-litmus-mcp-server ``` Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent. ## About # Litmus MCP Server The official [Litmus Automation](https://litmus.io) **Model Context Protocol (MCP) Server** enables LLMs and intelligent systems to interact with [Litmus Edge](https://litmus.io/products/litmus-edge) for device configuration, monitoring, and management. It is built on top of the MCP SDK and adheres to the [Model Context Protocol spec](https://modelcontextprotocol.io/). ## Table of Contents - [Quick Launch](#quick-launch) - [Web UI](#web-ui) - [Persistent Configuration](#persistent-configuration) - [Claude Code CLI](#claude-code-cli) - [Cursor IDE](#cursor-ide) - [VS Code / Copilot](#vs-code--github-copilot) - [Windsurf](#windsurf) - [STDIO - Claude Desktop](#stdio-with-claude-desktop) - [Tips](#Tips) - [Tools](#available-tools) - [Litmus Central](#litmus-central) --- ## Quick Launch ### Start an HTTP SSE MCP Server using Docker Run the server in Docker (HTTP SSE only) ```bash docker run -d --name litmus-mcp-server -p 8000:8000 ghcr.io/litmusautomation/litmus-mcp-server:latest ``` NOTE: The Litmus MCP Server is built for linux/AMD64 platforms. If running in Docker on ARM64, specify the AMD64 platform type by including the --platform argument: ```bash docker run -d --name litmus-mcp-server --platform linux/amd64 -p 8000:8000 ghcr.io/litmusautomation/litmus-mcp-server:main ``` --- ## Web UI The Docker image includes a built-in chat interface that lets you interact with Litmus Edge using natural language — no MCP client configuration required. Start the server with both ports exposed: ```bash docker run -d --name litmus-mcp-server \ -p 8000:8000 -p 9000:9000 \ -e ANTHROPIC_API_KEY= \ ghcr.io/litmusautomation/litmus-mcp-server:latest ``` - **`:9000`** — Web UI (chat interface). Open `http://localhost:9000` in your browser, add a Litmus Edge instance via the config page, and start chatting. - **`:8000`** — SSE endpoint for external MCP clients (Claude Desktop, Cursor, VS Code, etc.) — still available as normal. **Supported LLM providers:** Anthropic Claude, OpenAI, and Google Gemini. Provide one or more keys at startup (`ANTHROPIC_API_KEY`, `OPENAI_API_KEY`, `GEMINI_API_KEY`) or enter them through the Web UI's setup screen. The active provider and model are switchable from the Web UI's config page at any time. **Multiple Litmus Edge instances:** The Web UI lets you register and switch between multiple Litmus Edge devices from a single MCP server. Each instance keeps its own URL and OAuth2 credentials; the active instance's credentials are mirrored into `EDGE_URL` / `EDGE_API_CLIENT_ID` / `EDGE_API_CLIENT_SECRET` automatically. Manage instances under **Config → Litmus Edge Instances**, or check status per-instance from the **Health** page. **Live Litmus documentation as MCP Resources:** The server exposes `litmus://docs/` URIs that fetch live content from [docs.litmus.io](https://docs.litmus.io) on demand, so MCP-aware clients can pull current reference material directly into the model's context. If you deploy the MCP server and web client on separate hosts, set `MCP_SSE_URL` to point the web client at the server: ```bash -e MCP_SSE_URL=http://:8000/sse ``` ### Persistent Configuration By default, configuration saved through the Web UI (API keys, Litmus Edge instances, model preferences, connection settings) is written to `.env` inside the container and is lost when the container is removed. To retain configuration across container restarts and replacements, mount a host file over `/app/.env`: ```bash # One-time setup — the host file must exist before docker run mkdir -p /opt/litmus-mcp touch /opt/litmus-mcp/.env # Run with the volume mount docker run -d --name litmus-mcp-server \ -p 8000:8000 -p 9000:9000 \ -v /opt/litmus-mcp/.env:/app/.env \ ghcr.io/litmusautomation/litmus-mcp-server:latest ``` Any configuration you save in the UI is written to `/opt/litmus-mcp/.env` on the host. A new container started with the same `-v` flag will pick it up automatically on startup. > **Note:** The host-side file must be created with `touch` before running the container. If it does not exist, Docker creates a directory at that path and the application will fail to write configuration. **Docker Compose equivalent:** ```yaml services: litmus-mcp-server: image: ghcr.io/litmusautomation/litmus-mcp-server:latest ports: - "8000:8000" - "9000:9000" volumes: - /opt/litmus-mcp/.env:/app/.env ``` --- ### Claude Code CLI Run Claude from a directory that includes a configuration file at `~/.claude/mcp.json`: ```json { "mcpServers": { "litmus-mcp-server": { "type": "sse", "url": "http://localhost:8000/sse", "headers": { "EDGE_URL": "${EDGE_URL}", "EDGE_API_CLIENT_ID": "${EDGE_API_CLIENT_ID}", "EDGE_API_CLIENT_SECRET": "${EDGE_API_CLIENT_SECRET}", "NATS_SOURCE": "${NATS_SOURCE}", "NATS_PORT": "${NATS_PORT:-4222}", "NATS_USER": "${NATS_USER}", "NATS_PASSWORD": "${NATS_PASSWORD}", "INFLUX_HOST": "${INFLUX_HOST}", "INFLUX_PORT": "${INFLUX_PORT:-8086}", "INFLUX_DB_NAME": "${INFLUX_DB_NAME:-tsdata}", "INFLUX_USERNAME": "${INFLUX_USERNAME}", "INFLUX_PASSWORD": "${INFLUX_PASSWORD}" } } } } ``` [Anthropic Docs](https://docs.anthropic.com/en/docs/agents-and-tools/mcp) --- ### Cursor IDE Add to `~/.cursor/mcp.json` or `.cursor/mcp.json`: ```json { "mcpServers": { "litmus-mcp-server": { "url": "http://:8000/sse", "headers": { "EDGE_URL": "https://", "EDGE_API_CLIENT_ID": "", "EDGE_API_CLIENT_SECRET": "", "NATS_SOURCE": "", "NATS_PORT": "4222", "NATS_USER": "", "NATS_PASSWORD": "", "INFLUX_HOST": "", "INFLUX_PORT": "8086", "INFLUX_DB_NAME": "tsdata", "INFLUX_USERNAME": "", "INFLUX_PASSWORD": "" } } } } ``` [Cursor docs](https://docs.cursor.com/context/model-context-protocol) --- ### VS Code / GitHub Copilot #### Manual Configuration In VS Code: Open User Settings (JSON) → Add: ```json { "mcpServers": { "litmus-mcp-server": { "url": "http://:8000/sse", "headers": { "EDGE_URL": "https://", "EDGE_API_CLIENT_ID": "", "EDGE_API_CLIENT_SECRET": "", "NATS_SOURCE": "", "NATS_PORT": "4222", "NATS_USER": "", "NATS_PASSWORD": "", "INFLUX_HOST": "", "INFLUX_PORT": "8086", "INFLUX_DB_NAME": "tsdata", "INFLUX_USERNAME": "", "INFLUX_PASSWORD": "" } } } } ``` Or use `.vscode/mcp.json` in your project. [VS Code MCP Docs](https://code.visualstudio.com/docs/copilot/chat/mcp-servers) --- ### Windsurf Add to `~/.codeium/windsurf/mcp_config.json`: ```json { "mcpServers": { "litmus-mcp-server": { "url": "http://:8000/sse", "headers": { "EDGE_URL": "https://", "EDGE_API_CLIENT_ID": "", "EDGE_API_CLIENT_SECRET": "", "NATS_SOURCE": "", "NATS_PORT": "4222", "NATS_USER": "", "NATS_PASSWORD": "", "INFLUX_HOST": "", "INFLUX_PORT": "8086", "INFLUX_DB_NAME": "tsdata", "INFLUX_USERNAME": "", "INFLUX_PASSWORD": "" } } } } ``` [Windsurf MCP Docs](https://docs.windsurf.com/windsurf/mcp) ## STDIO with Claude Desktop This MCP server supports local connections with Claude Desktop and other applications via Standard file Input/Output (STDIO): https://modelcontextprotocol.io/legacy/concepts/transports To use STDIO: Clone, edit config.py to enable STDIO, run the server as a local process, and update Claude Desktop MCP server configuration file to use the server: ### Clone ```bash # Clone git clone https://github.com/litmusautomation/litmus-mcp-server.git ``` ### Set ENABLE_STDIO to 'true' in /src/config.py: ```python ENABLE_STDIO = os.getenv("ENABLE_STDIO", "true").lower() in ("true", "1", "yes") ``` ### Run the server ```bash # Run using uv uv sync cd /path/to/litmus-mcp-server uv run python3 src/server.py # Otherwise cd litmus-mcp-server pip install -e . python3 src/server.py ``` ### Add json server definision to your Claude Desktop config file: - macOS: `~/Library/Application Support/Claude/claude_desktop_config.json` - Windows: `%APPDATA%\Claude\claude_desktop_config.json` - Linux: `~/.config/Claude/claude_desktop_config.json` ```json { "mcpServers": { "litmus-mcp-server": { "command": "/path/to/.venv/bin/python3", "args": [ "/absolute/path/to/litmus-mcp-server/src/server.py" ], "env": { "PYTHONPATH": "/absolute/path/to/litmus-mcp-server/src", "EDGE_URL": "https://", "EDGE_API_CLIENT_ID": "", "EDGE_API_CLIENT_SECRET": "", "NATS_SOURCE": "", "NATS_PORT": "4222", "NATS_USER": "", "NATS_PASSWORD": "", "INFLUX_HOST": "", "INFLUX_PORT": "8086", "INFLUX_DB_NAME": "tsdata", "INFLUX_USERNAME": "", "INFLUX_PASSWORD": "" } } } } ``` ## Tips For development, use Python **Virtual environments**, for example to bridge mcp lib version diffs between dev clients like 'npx @modelcontextprotocol/inspector' & litmus-mcp-server ```json { "mcpServers": { "litmus-mcp-server": { "command": "/absolute/path/to/litmus-mcp-server/.venv/bin/python", "args": ["/absolute/path/to/litmus-mcp-server/src/server.py"], "env": { /* same as above */ } } } } ``` See [claude_desktop_config_venv.example.json](claude_desktop_config_venv.example.json) for the complete template. **Header Configuration Guide:** - `EDGE_URL`: Litmus Edge base URL (include https://) - `EDGE_API_CLIENT_ID` / `EDGE_API_CLIENT_SECRET`: OAuth2 credentials from Litmus Edge - `NATS_SOURCE`: Litmus Edge IP (no http/https) - `NATS_USER` / `NATS_PASSWORD`: Access token credentials from **System → Access Control → Tokens** - `INFLUX_HOST`: Litmus Edge IP (no http/https) - `INFLUX_USERNAME` / `INFLUX_PASSWORD`: DataHub user credentials --- ## Available Tools 57 tools across 11 categories. Tools accept structured arguments and return JSON. | Category | Function Name | Description | |---------------------------|----------------------------------------|-------------| | **DeviceHub, Devices** | `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 specified driver and default configuration. | | | `get_device_connection_status` ** | Check whether devices are actively publishing data via InfluxDB heartbeat (connected/stale/no_data). | | **DeviceHub, Tags** | `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. | | | `create_devicehub_tag` | Create a new tag (register) on a device. Driver-required properties auto-fill from defaults. | | | `update_devicehub_tag` | Update mutable fields of an existing tag (display name, description, properties). | | | `delete_devicehub_tag` | Delete a tag from a device. Destructive. | | | `get_tag_status` | Return OK/ERROR status for tags on a specific device. Optionally filter to a single tag. | | | `get_all_tags_status` | Return tag status across all devices. Defaults to non-OK only so issues surface first. | | **Device Identity** | `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. | | **Cloud / LEM Activation**| `get_cloud_activation_status` | Check cloud registration and Litmus Edge Manager (LEM) connection status. | | **Docker Management** | `get_all_containers_on_litmusedge` | List all Docker containers running on Litmus Edge Marketplace. | | | `run_docker_container_on_litmusedge` | Deploy and run a new Docker container on Litmus Edge Marketplace. | | **NATS Topics** * | `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. | | **InfluxDB / Time Series** ** | `get_historical_data_from_influxdb` | Query historical time-series data from InfluxDB by measurement and time range. | | | `list_influxdb_measurements` | List all measurement names in the `tsdata` database, discovery for downstream queries. | | | `get_device_historical_data` | Fuzzy-match device names to InfluxDB measurements and pull historical data per match. | | | `query_tag_data` | Query historical data for a specific tag by resolving its output topic. Newest-first. | | | `get_tag_statistics` | Aggregate stats for a tag: mean, min, max, stddev, count, plus baseline range (mean +/- 2 sigma). | | | `get_device_data_for_inference` | Composite payload for AI inference: device metadata, all tags, per-tag stats, and recent samples. | | **System, Events** | `get_system_events` | Retrieve system events filtered by time range, component, and severity (INFO/WARN/ALERT/ERROR). | | | `get_system_event_stats` | Event manager statistics: queue sizes, processing rates, memory, health indicators. | | **System, Network** | `get_firewall_rules` | Return configured firewall rules: ports, protocols, ALLOW/DENY actions. | | | `get_network_interface_info` | Network interface details: IP, MAC, gateway, link status, MTU, speed. Defaults to `eth0`. | | | `get_packet_capture_interfaces` | List network interfaces available for packet capture. | | | `get_packet_capture_status` | Current packet capture state and list of captured `.pcap` files with metadata. | | | `start_packet_capture` | Start a packet capture on an interface. Duration 1-30 minutes. | | | `stop_packet_capture` | Stop an in-progress packet capture. | | **Digital Twins** | `list_digital_twin_models` | List all Digital Twin models with ID, name, description, and version. | | | `create_digital_twin_model` | Create a new Digital Twin model. | | | `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 (fixed key-value pairs) for a model or instance. | | | `list_dynamic_attributes` | List dynamic attributes (real-time data points) for a model or instance. | | | `list_transformations` | List … ## Source & license This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code. - **Author:** [litmusautomation](https://github.com/litmusautomation) - **Source:** [litmusautomation/litmus-mcp-server](https://github.com/litmusautomation/litmus-mcp-server) - **License:** Apache-2.0 - **Homepage:** https://litmus.io/ Install and usage instructions live in the source repository linked above. ## Pricing - **Free** — Free ## Security capabilities Automated source analysis of v0.1.0 — what this tool can access: - **Network access:** no - **Filesystem access:** no - **Shell / process execution:** no - **Environment & secrets:** yes - **Dynamic code execution:** no *"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.* ## Versions - **0.1.0** — security scan: passed — Imported from the upstream source. ## Links - Listing page: https://agentstack.voostack.com/l/mcp-litmusautomation-litmus-mcp-server - Seller: https://agentstack.voostack.com/s/litmusautomation - Browse the marketplace: https://agentstack.voostack.com/browse --- Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.