sylvia-iot-mcp
Exposes sylvia-iot-core management APIs as tools for AI assistants, enabling IoT platform management via natural language.
README
sylvia-iot-mcp
An MCP server that exposes sylvia-iot-core management APIs as tools for AI assistants (Claude, etc.).
Note: This project is a practice ground for AI-assisted development using Claude Code with a spec-driven workflow powered by OpenSpec.
Features
66 tools across 10 capability areas:
| Category | Tools |
|---|---|
| Auth | auth_tokeninfo, user_get, user_update |
| OAuth2 Clients | client_create/count/list/get/update/delete |
| Units | unit_create/count/list/get/update/delete |
| Applications | application_create/count/list/get/update/delete/stats, application_send_dldata |
| Networks | network_create/count/list/get/update/delete/stats, network_send_uldata |
| Devices | device_create/count/list/get/update/delete, bulk and range create/delete |
| Device Routes | device_route_create/count/list/delete, bulk and range create/delete |
| Network Routes | network_route_create/count/list/delete |
| Downlink Buffer | dldata_buffer_count/list/delete |
| Data | application/network uplink/downlink data counts and lists, coremgr operation logs |
Requirements
- Node.js >= 18
- A running sylvia-iot-core instance
- An OAuth2 client with
client_credentialsgrant enabled
Setup
1. Create an OAuth2 client
The MCP server authenticates to sylvia-iot-core using the client_credentials grant. You need a private (confidential) client with this grant enabled.
If you have admin access, you can create one via the sylvia-iot-auth API or management UI.
2. Configure environment variables
Copy .env.example to .env and fill in your values:
cp .env.example .env
SYLVIA_IOT_AUTH_URL=http://your-host/auth
SYLVIA_IOT_COREMGR_URL=http://your-host/coremgr
SYLVIA_IOT_DATA_URL=http://your-host/data
SYLVIA_IOT_CLIENT_ID=your-client-id
SYLVIA_IOT_CLIENT_SECRET=your-client-secret
The URL defaults point to a local sylvia-iot-core instance started with default settings.
3. Run the server
npm install
node src/index.js
Claude Code / Claude Desktop Integration
Add the server to your MCP config (e.g. ~/.claude.json for Claude Code).
Via npx (no installation required):
{
"mcpServers": {
"sylvia-iot": {
"command": "npx",
"args": ["-y", "github:woofdogtw/sylvia-iot-mcp"],
"env": {
"SYLVIA_IOT_AUTH_URL": "http://your-host/auth",
"SYLVIA_IOT_COREMGR_URL": "http://your-host/coremgr",
"SYLVIA_IOT_DATA_URL": "http://your-host/data",
"SYLVIA_IOT_CLIENT_ID": "your-client-id",
"SYLVIA_IOT_CLIENT_SECRET": "your-client-secret"
}
}
}
}
Via local checkout:
{
"mcpServers": {
"sylvia-iot": {
"command": "node",
"args": ["/path/to/sylvia-iot-mcp/src/index.js"],
"env": {
"SYLVIA_IOT_AUTH_URL": "http://your-host/auth",
"SYLVIA_IOT_COREMGR_URL": "http://your-host/coremgr",
"SYLVIA_IOT_DATA_URL": "http://your-host/data",
"SYLVIA_IOT_CLIENT_ID": "your-client-id",
"SYLVIA_IOT_CLIENT_SECRET": "your-client-secret"
}
}
}
}
Once connected, you can manage your IoT platform conversationally:
"List all units", "Create a new application for unit X", "Show me the latest uplink data from network Y"
Authentication
The server uses OAuth2 client_credentials grant to obtain a bearer token. The token is cached in memory and refreshed automatically on expiry or 401 responses. No user login is required.
Development
# Watch mode
npm run dev
# Run end-to-end tests (requires running sylvia-iot-core)
node test-mcp.mjs
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.