"Local AI Agent Toolkit" matching MCP servers:

MCP server that provides live facility data access and operational tools, enabling the AI agent to query sensor readings, HVAC status, energy usage, alerts, and execute confirmed maintenance actions.

Carbon-aware MCP scheduler that defers "do it later" / "by tomorrow" / "overnight" LLM tasks to the cleanest electricity-grid hour inside a deadline — 40-70% lower CO2 per task, 50% cheaper via Anthropic/OpenAI Batch APIs. 9 MCP tools, per-task carbon receipts to local SQLite, Apache-2.0.

Tether MOS site telemetry, mining intelligence, and energy arbitrage agent.

Enables calculation of the most economical fuel (gasoline, ethanol, or natural gas) based on prices and vehicle consumption, following the 70% rule for ethanol and 60% for GNV.

An AI-powered EV Digital Twin platform for battery health monitoring, predictive maintenance, fleet analytics, and intelligent decision support using MCP tools for SOH prediction and RUL estimation.

Exposes EnergyPlus building simulation tools as MCP endpoints, enabling LLMs to run closed-loop energy optimization while maintaining occupant comfort.

Enables multi-agent orchestration of distributed energy resources through MCP tools, including simulation, real-time telemetry, dispatch control, and deterministic safety gatekeeping for grid support and demand response.

Provides read-only access to Shelly Cloud energy data, including live power, lifetime energy, and historical consumption with cost, enabling AI agents to monitor electricity usage without device control.

An unofficial read-only MCP server for Panasonic AiSEG2 home energy management controllers, enabling clients to read live power flow, per-circuit consumption, circuit names, daily totals, and historical energy/cost data from the device's local web interface.

An MCP server that lets an MCP client control IKEA TRÅDFRI smart plugs paired to a DIRIGERA hub via its local REST API.

Read-only MCP server for Home Assistant that computes statistical summaries, trends, and session detection from recorded sensor history, returning compact tables instead of raw data so small local models can answer questions about energy usage, climate, and appliance activity without token-heavy arithmetic.

Enables AI assistants to control a Homey Pro smart home hub, create automation flows from natural language, and query device and energy history.

Live and historical electricity prices, demand, generation mix and carbon intensity for 25 grid zones (US, Europe, GB, Australia). Hosted endpoint plus local stdio bridge; free sample mode, free API key, or x402 pay-per-call.

Enables discovery and control of Philips Hue lighting devices via a local bridge using the CLIP v2 API, without any cloud dependency.

AI assistants can size heat pumps, estimate energy costs, and verify cold-climate performance using bundled data and no API keys.

Enables AI agents to query live solar telemetry from public SolarNetwork sites, detect dated equipment faults with peer-relative analysis, and generate printable PDF service reports for field technicians.

Exposes a single read-only tool that retrieves live Huawei SUN2000 inverter telemetry over local Modbus TCP, including model, firmware, active power, daily and lifetime yield, device status, and observation timing. Readings are briefly cached, with failures returned as errors rather than stale or fabricated values.

Sourced carbon emission factors + audit-traced calculations an AI can cite.

Enables AI agents to choose the lowest-carbon cloud region for a workload, with tools for ranking regions by carbon intensity and latency, and for finding optimal start times to reduce emissions.

Connect AI assistants to Victron Energy systems to read real-time solar, battery, grid, and inverter data from your local network via Modbus TCP or MQTT.