s7-mcp-server by cadugrillo - MCP Server

S7 MCP SERVER

S7 MCP SERVER is a MCP Server that connects AI agents to Siemens industrial PLCs (specifically S7-1500 and S7-1200 models). This allows AI agents to automatically monitor and control industrial equipment by sending commands and receiving data from the machines.

🔧 Available Tools

User authentication (login, logout, ChangePassword-user)
Check PLC connectivity (ping)
Retrieve user permissions (Api-GetPermissions)
Get API version (Api-Version)
List available API methods (Api-Browse)
Retrieve structure information (Api-GetQuantityStructures)
Get password security policies (Api-GetPasswordPolicy)
Browse tags and metadata (PlcProgram-Browse)
Read single variables (PlcProgram-Read)
Write Boolean, Number, or String tags (PlcProgram-Write)
Read the current CPU operating mode (Plc-ReadOperatingMode)
Request a change of operating mode (Plc-RequestChangeOperatingMode)
Read the CPU system time (Plc-ReadSystemTime)
Set the CPU system time (Plc-SetSystemTime)
Read available project languages (Project-ReadLanguages)
Browse active alarms (Alarms-Browse)
Acknowledge alarms (Alarms-Acknowledge)
Browse diagnostic buffer entries (DiagnosticBuffer-Browse)

⚙️ Prerequisites

Node.js (v18.x or later recommended)
npm (comes bundled with Node.js)
Access to a running SIEMENS PLC API (Webserver)

⚙️ Configuration

This server uses environment variables for configuration.

Example `env variables`:

export PLC_IP_ADDRESSES="192.168.2.200, 192.168.2.201, 192.168.2.202"
export PLC_NAMES="PLC1, PLC2, PLC3" //optional
export MCP_SERVER_PORT=5000 //optional
export TRANSPORT="streamable-http" //optional
export NODE_TLS_REJECT_UNAUTHORIZED=0

🚀 Getting Started (Development)

Git Clone this repo: https://github.com/cadugrillo/s7-mcp-server.git
Navigate to the project folder:

cd s7-mcp-server

Install dependencies:

npm install

Edit env variables as shown above.
Start the server

npm run dev

🐳 Docker Container

There is a Docker Container Image avaiable at https://hub.docker.com/r/cadugrillo/s7-mcp-server/tags

How to run

docker run -dp 5000:5000 -m 512m --memory-swap=512m \
--name s7mcp \
-e MCP_SERVER_PORT=5000 \
-e PLC_IP_ADDRESSES="192.168.2.200, 192.168.2.201, 192.168.2.202" \
-e PLC_NAMES="PLC1, PLC2, PLC3" \
-e NODE_TLS_REJECT_UNAUTHORIZED=0 \
cadugrillo/s7-mcp-server:latest

Remember to change port according to your deployment.

Available Environment Variables


PLC_IP_ADDRESSES	required	IP addresses of available PLCs separated by comma eg. "192.168.1.10, 192.168.1.20"
PLC_NAMES	optional	Names of available PLCs separated by comma eg. "Machine1, Machine2"
MCP_SERVER_PORT	optional	If not set, it defaults to 5000
TRANSPORT	optional	It can be "streamable-http" or "stdio". If not set it defaults to streamable-http
NODE_TLS_REJECT_UNAUTHORIZED	required	Always to set to 0 for bypassing certificate validation

🖥️ Connecting with Claude Desktop

To use this MCP server with Claude AI (desktop version):

Find or create the claude_desktop_config.json file (typically in the Claude app config folder).
Add or update the following if running in a container (streamable-http) (remember to change port according to your deployment):

{
  "mcpServers": {
    "S7-MCP-SERVER": {
      "command": "npx",
      "args": ["mcp-remote", "http://localhost:5000/mcp"]
    }
  }
}

Or use the following if running locally (stdio):

{
  "mcpServers": {
    "S7-MCP-SERVER": {
      "command": "node",
      "args": ["path/to/your/s7McpServer.js"], //`for Windows user proper escape (eg. C:\\path\\to\\your\\s7McpServer.js)`
      "env": {
        "PLC_IP_ADDRESSES":"192.168.2.200, 192.168.2.201, 192.168.2.202",
        "PLC_NAMES":"PLC1, PLC2, PLC3",
        "TRANSPORT": "stdio",
        "NODE_TLS_REJECT_UNAUTHORIZED": "0"
      }
    }
  }
}

🪲 Reporting bugs and contributing

Want to report a bug or request a feature? Please open an issue