SiLA MCP Server
Enables AI assistants to interact with laboratory devices via a SiLA server, allowing querying device info, listing commands, executing commands, and monitoring status.
README
SiLA MCP Server
A Model Context Protocol (MCP) server that acts as a bridge between Claude (or other MCP clients) and an existing SiLA server controlling lab devices.
Overview
This MCP server exposes laboratory device functionality through the MCP protocol, allowing AI assistants to:
- Query device information and status
- List available commands
- Execute device commands
- Monitor device parameters in real-time
Prerequisites
- Node.js 18+
- A running SiLA server with REST API endpoints
- npm or yarn
Installation
- Clone or download this project
- Install dependencies:
npm install
- Build the TypeScript code:
npm run build
Configuration
The server reads configuration from environment variables:
SILA_SERVER_URL: The URL of your SiLA server (default:http://localhost:50051)SILA_SERVER_INSECURE: Whether to allow insecure connections (default:true)
Example:
export SILA_SERVER_URL=http://192.168.1.100:50051
export SILA_SERVER_INSECURE=false
Running the Server
Development mode (with auto-rebuild):
npm run watch
Production mode:
npm start
MCP Capabilities
Tools
- get_device_info: Retrieve device information including name, type, manufacturer, serial number, and firmware version
- list_device_commands: Get all available commands the device supports
- execute_command: Execute a command on the device with optional parameters
- get_device_status: Get real-time device status including operational state
Resources
- sila://device/info: Device metadata and capabilities (read-only)
- sila://device/status: Current device status (read-only)
Integration with Claude
To use this MCP server with Claude, add it to your MCP configuration:
{
"mcpServers": {
"sila": {
"command": "node",
"args": ["path/to/build/index.js"],
"env": {
"SILA_SERVER_URL": "http://localhost:50051"
}
}
}
}
SiLA Server Requirements
Your SiLA server should provide the following REST API endpoints:
GET /health- Health check endpointGET /device/info- Device informationGET /device/status- Device statusGET /device/commands- List available commandsPOST /device/commands/{commandName}- Execute a commandGET /device/parameters/{parameterName}- Get parameter valuePUT /device/parameters/{parameterName}- Set parameter value
Project Structure
.
├── src/
│ ├── index.ts # Main MCP server implementation
│ └── sila-client.ts # SiLA server client library
├── build/ # Compiled JavaScript (generated)
├── package.json
├── tsconfig.json
└── README.md
Development
Build for production:
npm run build
Watch mode (recommended for development):
npm run watch
Troubleshooting
Connection Issues
- Verify the SiLA server is running at the configured URL
- Check firewall rules allow communication
- Enable debug logging by setting
DEBUG=*
Missing Device Endpoints
- Ensure your SiLA server implements all required REST endpoints
- Check the endpoint paths match the expected format
- Review SiLA server documentation
License
MIT
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.