emoncms-mcp-server
MCP server for EmonCMS energy monitoring API, enabling AI assistants to query energy feeds, inputs, and historical data.
README
emoncms-mcp-server
MCP (Model Context Protocol) server for the EmonCMS energy monitoring API. Allows AI assistants to query energy feeds, inputs, and historical data from your EmonCMS instance.
Features
- feed_list — List all feeds with current values and units
- feed_value — Get the current value of a specific feed
- feed_fetch — Get current values for multiple feeds at once
- feed_data — Get historical time-series data with configurable intervals
- feed_average — Get averaged data over time periods (hourly, daily, etc.)
- feed_daily — Get daily data points aligned to timezone (ideal for kWh/day)
- feed_meta — Get feed metadata (start time, interval, number of points)
- input_list — List all inputs grouped by node
- input_get — Get inputs for a specific node
Installation
npm install
npm run build
Configuration
The server requires two environment variables:
| Variable | Required | Description |
|---|---|---|
EMONCMS_URL |
No | Base URL of your EmonCMS instance (default: http://192.168.1.250/emoncms) |
EMONCMS_APIKEY |
Yes | Your EmonCMS read API key |
Usage with OpenCode
Add to your ~/.config/opencode/opencode.json:
{
"mcpServers": {
"emoncms": {
"type": "stdio",
"command": "node",
"args": ["/path/to/emoncms-mcp-server/dist/index.js"],
"env": {
"EMONCMS_URL": "http://192.168.1.250/emoncms",
"EMONCMS_APIKEY": "your-read-api-key"
}
}
}
}
Usage with Claude Desktop
Add to ~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"emoncms": {
"command": "node",
"args": ["/path/to/emoncms-mcp-server/dist/index.js"],
"env": {
"EMONCMS_URL": "http://192.168.1.250/emoncms",
"EMONCMS_APIKEY": "your-read-api-key"
}
}
}
}
Tool Reference
feed_list
Lists all feeds with their current values.
No parameters required.
feed_value
Get the current value of a single feed.
| Parameter | Type | Description |
|---|---|---|
id |
number | Feed ID |
feed_fetch
Get current values for multiple feeds.
| Parameter | Type | Description |
|---|---|---|
ids |
number[] | Array of feed IDs |
feed_data
Get historical time-series data.
| Parameter | Type | Description |
|---|---|---|
id |
number | Feed ID |
start |
string | Start time — ISO 8601 (e.g. 2024-01-01T00:00:00Z) or relative (-24h, -7d) |
end |
string? | End time (default: now) |
interval |
number? | Seconds between data points (default: 600) |
feed_average
Get averaged data over intervals.
| Parameter | Type | Description |
|---|---|---|
id |
number | Feed ID |
start |
string | Start time |
end |
string? | End time (default: now) |
interval |
number | Averaging interval in seconds (e.g. 3600 for hourly) |
feed_daily
Get daily data points (timezone-aligned).
| Parameter | Type | Description |
|---|---|---|
id |
number | Feed ID |
start |
string | Start time (e.g. -30d) |
end |
string? | End time (default: now) |
feed_meta
Get metadata for a feed.
| Parameter | Type | Description |
|---|---|---|
id |
number | Feed ID |
input_list
Lists all inputs grouped by node.
No parameters required.
input_get
Get inputs for a specific node.
| Parameter | Type | Description |
|---|---|---|
node |
string | Node name (e.g. emonpi, emontx3) |
Development
npm run dev # Run with tsx (hot reload)
npm run build # Compile TypeScript
npm start # Run compiled version
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.